Accept ill-formed UTF-8 in all binary readers again

RFC 8949 and the MessagePack/BSON/UBJSON/BJData specs leave UTF-8
well-formedness checking up to the decoder, so following #5529 the
binary readers are lenient by default again, as in release 3.12.0
(the reader-side check was added by #5185/#5531, not in any release);
reader-side validation becomes opt-in in a follow-up PR. The writers
stay strict and throw type_error.316 for ill-formed UTF-8. BON8 is
unchanged, since UTF-8 lead bytes are structural there.

Signed-off-by: Niels Lohmann <mail@nlohmann.me>

.clang-tidy

@@ -1,9 +1,15 @@
-# TODO: The first three checks are only removed to get the CI going. They have to be addressed at some point.
-# TODO: portability-avoid-pragma-once: should be fixed eventually
+# bugprone-use-after-move (hicpp-invalid-access-moved is its alias) still flags
+# the basic_json move constructor, which forwards the whole object to its base
+# class (#5724), and two forwards in the error-message construction of
+# at(KeyType&&) (json.hpp, both overloads: find(std::forward<KeyType>(key))
+# followed by string_t(std::forward<KeyType>(key)) in the throw), which #5689
+# rewrites. Re-enable both checks once those changes have landed.
+# portability-avoid-pragma-once: kept disabled on purpose. #pragma once is accepted
+# by every supported compiler, and tools/amalgamate/amalgamate.py strips it from
+# single_include, so there is nothing left to fix here.
 
 Checks: '*,
 
-         -portability-template-virtual-member-function,
          -bugprone-use-after-move,
          -hicpp-invalid-access-moved,
 
@@ -37,7 +43,6 @@ Checks: '*,
          -google-readability-function-size,
          -google-runtime-float,
          -google-runtime-int,
-         -google-runtime-references,
          -hicpp-avoid-goto,
          -hicpp-explicit-conversions,
          -hicpp-function-size,
@@ -71,6 +76,7 @@ Checks: '*,
          -readability-magic-numbers,
          -readability-redundant-access-specifiers,
          -readability-redundant-parentheses,
+         -readability-redundant-typename,
          -readability-simplify-boolean-expr,
          -readability-uppercase-literal-suffix,
          -readability-use-concise-preprocessor-directives'
@@ -81,5 +87,4 @@ CheckOptions:
 
 WarningsAsErrors: '*'
 
-#HeaderFilterRegex: '.*nlohmann.*'
 HeaderFilterRegex: '.*hpp$'

.github/workflows/ubuntu.yml

@@ -85,7 +85,7 @@ jobs:
 
   ci_static_analysis_clang:
     runs-on: ubuntu-latest
-    container: silkeh/clang:dev
+    container: silkeh/clang:22
     strategy:
       matrix:
         target: [ci_test_clang, ci_clang_tidy, ci_test_clang_sanitizer, ci_clang_analyze, ci_single_binaries]

.reuse/dep5

@@ -23,10 +23,6 @@ Files: tests/thirdparty/fifo_map/*
 Copyright: 2015-2017 Niels Lohmann
 License: MIT
 
-Files: tests/thirdparty/Fuzzer/*
-Copyright: 2003-2022 LLVM Project.
-License: Apache-2.0
-
 Files: tests/thirdparty/imapdl/*
 Copyright: 2017 Georg Sauthoff <mail@gms.tf>
 License: GPL-3.0-only

cmake/ci.cmake

@@ -8,24 +8,24 @@ set(N 10)
 include(FindPython3)
 find_package(Python3 COMPONENTS Interpreter)
 
-find_program(CLANG_TOOL NAMES clang++-HEAD clang++ clang++-20 clang++-19 clang++-18 clang++-17 clang++-16 clang++-15 clang++-14 clang++-13 clang++-12 clang++-11 clang++)
+find_program(CLANG_TOOL NAMES clang++-HEAD clang++ clang++-22 clang++-21 clang++-20 clang++-19 clang++-18 clang++-17 clang++-16 clang++-15 clang++-14 clang++-13 clang++-12 clang++-11 clang++)
 execute_process(COMMAND ${CLANG_TOOL} --version OUTPUT_VARIABLE CLANG_TOOL_VERSION ERROR_VARIABLE CLANG_TOOL_VERSION)
 string(REGEX MATCH "[0-9]+(\\.[0-9]+)+" CLANG_TOOL_VERSION "${CLANG_TOOL_VERSION}")
 message(STATUS "🔖 Clang ${CLANG_TOOL_VERSION} (${CLANG_TOOL})")
 
-find_program(CLANG_TIDY_TOOL NAMES clang-tidy-20 clang-tidy-19 clang-tidy-18 clang-tidy-17 clang-tidy-16 clang-tidy-15 clang-tidy-14 clang-tidy-13 clang-tidy-12 clang-tidy-11 clang-tidy)
+find_program(CLANG_TIDY_TOOL NAMES clang-tidy-22 clang-tidy-21 clang-tidy-20 clang-tidy-19 clang-tidy-18 clang-tidy-17 clang-tidy-16 clang-tidy-15 clang-tidy-14 clang-tidy-13 clang-tidy-12 clang-tidy-11 clang-tidy)
 execute_process(COMMAND ${CLANG_TIDY_TOOL} --version OUTPUT_VARIABLE CLANG_TIDY_TOOL_VERSION ERROR_VARIABLE CLANG_TIDY_TOOL_VERSION)
 string(REGEX MATCH "[0-9]+(\\.[0-9]+)+" CLANG_TIDY_TOOL_VERSION "${CLANG_TIDY_TOOL_VERSION}")
 message(STATUS "🔖 Clang-Tidy ${CLANG_TIDY_TOOL_VERSION} (${CLANG_TIDY_TOOL})")
 
 message(STATUS "🔖 CMake ${CMAKE_VERSION} (${CMAKE_COMMAND})")
 
-find_program(GCC_TOOL NAMES g++-latest g++-HEAD g++ g++-15 g++-14 g++-13 g++-12 g++-11 g++-10)
+find_program(GCC_TOOL NAMES g++-latest g++-HEAD g++ g++-16 g++-15 g++-14 g++-13 g++-12 g++-11 g++-10)
 execute_process(COMMAND ${GCC_TOOL} --version OUTPUT_VARIABLE GCC_TOOL_VERSION ERROR_VARIABLE GCC_TOOL_VERSION)
 string(REGEX MATCH "[0-9]+(\\.[0-9]+)+" GCC_TOOL_VERSION "${GCC_TOOL_VERSION}")
 message(STATUS "🔖 GCC ${GCC_TOOL_VERSION} (${GCC_TOOL})")
 
-find_program(GCOV_TOOL NAMES gcov-HEAD gcov gcov-15 gcov-14 gcov-13 gcov-12 gcov-11 gcov-10)
+find_program(GCOV_TOOL NAMES gcov-HEAD gcov gcov-16 gcov-15 gcov-14 gcov-13 gcov-12 gcov-11 gcov-10)
 execute_process(COMMAND ${GCOV_TOOL} --version OUTPUT_VARIABLE GCOV_TOOL_VERSION ERROR_VARIABLE GCOV_TOOL_VERSION)
 string(REGEX MATCH "[0-9]+(\\.[0-9]+)+" GCOV_TOOL_VERSION "${GCOV_TOOL_VERSION}")
 message(STATUS "🔖 GCOV ${GCOV_TOOL_VERSION} (${GCOV_TOOL})")

cmake/clang_flags.cmake

@@ -2,7 +2,6 @@
 # -Wno-c++98-compat               The library targets C++11.
 # -Wno-c++98-compat-pedantic      The library targets C++11.
 # -Wno-deprecated-declarations    The library contains annotations for deprecated functions.
-# -Wno-extra-semi-stmt            The library uses assert which triggers this warning.
 # -Wno-padded                     We do not care about padding warnings.
 # -Wno-covered-switch-default     All switches list all cases and a default case.
 # -Wno-c2y-extensions             Clang 22.1 diagnoses __COUNTER__ as a C2y extension, also in
@@ -20,7 +19,6 @@ set(CLANG_CXXFLAGS
     -Wno-c++98-compat
     -Wno-c++98-compat-pedantic
     -Wno-deprecated-declarations
-    -Wno-extra-semi-stmt
     -Wno-padded
     -Wno-covered-switch-default
     -Wno-c2y-extensions

cmake/gcc_flags.cmake

@@ -1,4 +1,4 @@
-# Warning flags determined for GCC 15.1.0 with https://github.com/nlohmann/gcc_flags:
+# Warning flags determined for GCC 16.2.0 with https://github.com/nlohmann/gcc_flags:
 # Ignored GCC warnings:
 # -Wno-abi-tag           We do not care about ABI tags.
 # -Wno-aggregate-return  The library uses aggregate returns.
@@ -16,6 +16,8 @@ set(GCC_CXXFLAGS
     --extra-warnings
     -W
     -WNSObject-attribute
+    -Wabbreviated-auto-in-template-arg
+    -Wabi
     -Wno-abi-tag
     -Waddress
     -Waddress-of-packed-member
@@ -64,6 +66,7 @@ set(GCC_CXXFLAGS
     -Wanalyzer-tainted-divisor
     -Wanalyzer-tainted-offset
     -Wanalyzer-tainted-size
+    -Wanalyzer-throw-of-unexpected-type
     -Wanalyzer-too-complex
     -Wanalyzer-undefined-behavior-ptrdiff
     -Wanalyzer-undefined-behavior-strtok
@@ -80,10 +83,13 @@ set(GCC_CXXFLAGS
     -Warith-conversion
     -Warray-bounds=2
     -Warray-compare
+    -Warray-parameter
     -Warray-parameter=2
     -Wattribute-alias=2
     -Wattribute-warning
     -Wattributes
+    -Wauto-profile
+    -Wbidi-chars=any
     -Wbool-compare
     -Wbool-operation
     -Wbuiltin-declaration-mismatch
@@ -99,6 +105,7 @@ set(GCC_CXXFLAGS
     -Wc++20-compat
     -Wc++20-extensions
     -Wc++23-extensions
+    -Wc++26-compat
     -Wc++26-extensions
     -Wc++2a-compat
     -Wcalloc-transposed-args
@@ -142,6 +149,7 @@ set(GCC_CXXFLAGS
     -Wdeprecated-enum-enum-conversion
     -Wdeprecated-enum-float-conversion
     -Wdeprecated-literal-operator
+    -Wdeprecated-openmp
     -Wdeprecated-variadic-comma-omission
     -Wdisabled-optimization
     -Wdiv-by-zero
@@ -156,21 +164,18 @@ set(GCC_CXXFLAGS
     -Wenum-conversion
     -Wexceptions
     -Wexpansion-to-defined
+    -Wexperimental-fmv-target
+    -Wexpose-global-module-tu-local
+    -Wexternal-tu-local
     -Wextra
     -Wextra-semi
     -Wflex-array-member-not-at-end
     -Wfloat-conversion
     -Wfloat-equal
-    -Wformat -Wformat-contains-nul
-    -Wformat -Wformat-diag
-    -Wformat -Wformat-extra-args
-    -Wformat -Wformat-nonliteral
-    -Wformat -Wformat-overflow=2
-    -Wformat -Wformat-security
-    -Wformat -Wformat-signedness
-    -Wformat -Wformat-truncation=2
-    -Wformat -Wformat-y2k
-    -Wformat -Wformat-zero-length
+    -Wformat-diag
+    -Wformat-overflow=2
+    -Wformat-signedness
+    -Wformat-truncation=2
     -Wformat=2
     -Wframe-address
     -Wfree-nonheap-object
@@ -197,6 +202,8 @@ set(GCC_CXXFLAGS
     -Winvalid-offsetof
     -Winvalid-pch
     -Winvalid-utf8
+    -Wkeyword-macro
+    -Wleading-whitespace=spaces
     -Wliteral-suffix
     -Wlogical-not-parentheses
     -Wlogical-op
@@ -227,6 +234,7 @@ set(GCC_CXXFLAGS
     -Wnarrowing
     -Wnoexcept
     -Wnoexcept-type
+    -Wnon-c-typedef-for-linkage
     -Wnon-template-friend
     -Wnon-virtual-dtor
     -Wnonnull
@@ -269,6 +277,8 @@ set(GCC_CXXFLAGS
     -Wscalar-storage-order
     -Wself-move
     -Wsequence-point
+    -Wsfinae-incomplete
+    -Wsfinae-incomplete=2
     -Wshadow=compatible-local
     -Wshadow=global
     -Wshadow=local
@@ -289,6 +299,7 @@ set(GCC_CXXFLAGS
     -Wstrict-aliasing=3
     -Wstrict-null-sentinel
     -Wstrict-overflow
+    -Wstrict-overflow=5
     -Wstring-compare
     -Wstringop-overflow
     -Wstringop-overflow=4
@@ -333,8 +344,8 @@ set(GCC_CXXFLAGS
     -Wunreachable-code
     -Wunsafe-loop-optimizations
     -Wunused
-    -Wunused-but-set-parameter
-    -Wunused-but-set-variable
+    -Wunused-but-set-parameter=3
+    -Wunused-but-set-variable=3
     -Wunused-const-variable=2
     -Wunused-function
     -Wunused-label

docs/mkdocs/docs/api/basic_json/to_bjdata.md

@@ -56,6 +56,8 @@ Strong guarantee: if an exception is thrown, there are no changes in the JSON va
 
 - Throws [`other_error.502`](../../home/exceptions.md#jsonexceptionother_error502) if `use_type` is true and `use_size`
   is false.
+- Throws [type_error.316](../../home/exceptions.md#jsonexceptiontype_error316) if a string or object key in `j` is
+  not valid UTF-8
 
 ## Complexity
 
@@ -89,4 +91,5 @@ Linear in the size of the JSON value `j`.
 ## Version history
 
 - Added in version 3.11.0.
-- BJData version parameter (for draft3 binary encoding) added in version 3.12.0.
+- BJData version parameter (for draft3 binary encoding) added in version 3.12.0.
+- Throwing `type_error.316` for a string or object key that is not valid UTF-8 added in version 3.13.0.

docs/mkdocs/docs/api/basic_json/to_bson.md

@@ -46,6 +46,8 @@ Strong guarantee: if an exception is thrown, there are no changes in the JSON va
 - Throws [`out_of_range.415`](../../home/exceptions.md#jsonexceptionout_of_range415) if the subtype of a binary value
   exceeds 255, the maximum of the BSON binary subtype; example:
   `"subtype 70000 is too large for the BSON binary subtype (max 255)"`
+- Throws [type_error.316](../../home/exceptions.md#jsonexceptiontype_error316) if a string or object key is
+  not valid UTF-8
 
 ## Complexity
 
@@ -82,3 +84,5 @@ pass before anything is written.
 - Added in version 3.4.0.
 - Linear in the size of `j`, and no longer limited by the call stack for deeply nested values, since version 3.13.0.
 - `out_of_range.415` is now detected before anything is written, like the other exceptions above, since version 3.13.0.
+- Throwing `type_error.316` for a string value or object key that is not valid UTF-8, detected before anything is
+  written, added in version 3.13.0.

docs/mkdocs/docs/api/basic_json/to_cbor.md

@@ -35,6 +35,11 @@ The exact mapping and its limitations are described on a [dedicated page](../../
 
 Strong guarantee: if an exception is thrown, there are no changes in the JSON value.
 
+## Exceptions
+
+- Throws [type_error.316](../../home/exceptions.md#jsonexceptiontype_error316) if a string or object key in `j` is
+  not valid UTF-8
+
 ## Complexity
 
 Linear in the size of the JSON value `j`.
@@ -68,3 +73,4 @@ Linear in the size of the JSON value `j`.
 
 - Added in version 2.0.9.
 - Compact representation of floating-point numbers added in version 3.8.0.
+- Throwing `type_error.316` for a string or object key that is not valid UTF-8 added in version 3.13.0.

docs/mkdocs/docs/api/basic_json/to_ubjson.md

@@ -49,6 +49,8 @@ Strong guarantee: if an exception is thrown, there are no changes in the JSON va
 
 - Throws [`other_error.502`](../../home/exceptions.md#jsonexceptionother_error502) if `use_type` is true and `use_size`
   is false.
+- Throws [type_error.316](../../home/exceptions.md#jsonexceptiontype_error316) if a string or object key in `j` is
+  not valid UTF-8
 
 ## Complexity
 
@@ -82,3 +84,4 @@ Linear in the size of the JSON value `j`.
 ## Version history
 
 - Added in version 3.1.0.
+- Throwing `type_error.316` for a string or object key that is not valid UTF-8 added in version 3.13.0.

docs/mkdocs/docs/features/binary_formats/bjdata.md

@@ -63,6 +63,12 @@ The library uses the following mapping from JSON values types to BJData types ac
 
       - strings with more than 18446744073709551615 bytes, i.e., 2<sup>64</sup>-1 bytes (theoretical)
 
+!!! warning "UTF-8 validation of string values and object keys"
+
+    BJData strings must use UTF-8 encoding. `to_bjdata()` validates the bytes of every string value and object key
+    and throws [`type_error.316`](../../home/exceptions.md#jsonexceptiontype_error316) for ill-formed UTF-8, so a
+    value with such a string cannot be serialized in the first place.
+
 !!! info "Unused BJData markers"
 
     The following markers are not used in the conversion:
@@ -208,6 +214,15 @@ The library maps BJData types to JSON value types as follows:
 
     The mapping is **complete** in the sense that any BJData value can be converted to a JSON value.
 
+!!! warning "Ill-formed UTF-8 in string values and object keys"
+
+    BJData strings must use UTF-8 encoding, but this is not enforced on read: `from_bjdata()` accepts a string
+    value or object key whose bytes are not valid UTF-8 and hands them back unchanged. However,
+    [`dump()`](../../api/basic_json/dump.md) still requires valid UTF-8 and throws
+    [`type_error.316`](../../home/exceptions.md#jsonexceptiontype_error316) for such a value, unless an error
+    handler is passed that replaces or ignores the ill-formed bytes. `to_bjdata()` is strict as well (see above), so
+    a value read this way cannot be written back to BJData.
+
 !!! info "Round trips"
 
     A value returned by [`from_bjdata`](../../api/basic_json/from_bjdata.md) can be serialized with

docs/mkdocs/docs/features/binary_formats/bson.md

@@ -109,14 +109,17 @@ The library maps BSON record types to JSON value types as follows:
     If BSON input must be validated for strict specification compliance, validate it separately before passing it to
     `from_bson()`.
 
-!!! warning "UTF-8 validation of string values"
+!!! warning "Ill-formed UTF-8 in string values"
 
-    The BSON specification requires `string` values (type `0x02`) to be valid UTF-8. This library validates the
-    bytes of every such string at decode time and rejects ill-formed UTF-8 with a
-    [`parse_error.113`](../../home/exceptions.md#jsonexceptionparse_error113) exception (or, with `allow_exceptions`
-    set to `false`, a discarded value), rather than only failing later when the resulting value is dumped. Element
-    (key) names and `binary` values (type `0x05`) are unaffected and are never validated, since they are read
-    byte-by-byte as a C string, or are not required to hold text, respectively.
+    The BSON specification requires `string` values (type `0x02`) to be valid UTF-8, but this is not required of a
+    decoder. `from_bson()` accepts a `string` value whose bytes are not valid UTF-8 and hands them back unchanged.
+    However, [`dump()`](../../api/basic_json/dump.md) still requires valid UTF-8 and throws
+    [`type_error.316`](../../home/exceptions.md#jsonexceptiontype_error316) for such a value, unless an error
+    handler is passed that replaces or ignores the ill-formed bytes. `to_bson()` is strict as well and throws the
+    same exception for a string value or element (key) name that is not valid UTF-8, so an object with such a key
+    or value cannot be produced in the first place, even though `from_bson()` would accept it from another source.
+    Element (key) names are never validated on read, since they are read byte-by-byte as a C string. `binary`
+    values (type `0x05`) are unaffected, since they are not required to hold text.
 
 ??? example
 

docs/mkdocs/docs/features/binary_formats/cbor.md

@@ -189,15 +189,16 @@ The library maps CBOR types to JSON value types as follows:
     ([RFC 8392](https://www.rfc-editor.org/rfc/rfc8392.html)), cannot be read with this library and need a
     general-purpose CBOR library instead.
 
-!!! warning "UTF-8 validation of text strings"
+!!! warning "Ill-formed UTF-8 in text strings"
 
     [RFC 8949, Section 3.1](https://www.rfc-editor.org/rfc/rfc8949.html#section-3.1) requires CBOR text strings
-    (major type 3) to be valid UTF-8. This library validates the bytes of every text string (object keys included) at
-    decode time and rejects ill-formed UTF-8 with a
-    [`parse_error.113`](../../home/exceptions.md#jsonexceptionparse_error113) exception (or, with
-    `allow_exceptions` set to `false`, a discarded value), rather than only failing later when the resulting value is
-    dumped. Byte strings (major type 2) are unaffected and are never validated, since they are not required to hold
-    text.
+    (major type 3) to be valid UTF-8, but leaves it up to the decoder whether to enforce this. This library does
+    not: `from_cbor()` accepts a text string (object keys included) whose bytes are not valid UTF-8 and hands them
+    back unchanged. However, [`dump()`](../../api/basic_json/dump.md) still requires valid UTF-8 and throws
+    [`type_error.316`](../../home/exceptions.md#jsonexceptiontype_error316) for such a value, unless an error
+    handler is passed that replaces or ignores the ill-formed bytes. `to_cbor()` is strict as well and throws the
+    same exception for a string value or object key that is not valid UTF-8, so such a value cannot be written back
+    to CBOR. Byte strings (major type 2) are unaffected, since they are not required to hold text.
 
 !!! warning "Tagged items"
 

docs/mkdocs/docs/features/binary_formats/messagepack.md

@@ -153,14 +153,15 @@ The library maps MessagePack types to JSON value types as follows:
     This applies to the [SAX interface](../parsing/sax_interface.md) as well, as the key is read before it is passed
     on. Such input needs a general-purpose MessagePack library instead.
 
-!!! warning "UTF-8 validation of string values"
+!!! warning "Ill-formed UTF-8 in string values"
 
-    The MessagePack specification requires `str` values (`fixstr`, `str 8`, `str 16`, `str 32`) to be valid UTF-8.
-    This library validates the bytes of every such string (object keys included) at decode time and rejects
-    ill-formed UTF-8 with a [`parse_error.113`](../../home/exceptions.md#jsonexceptionparse_error113) exception (or,
-    with `allow_exceptions` set to `false`, a discarded value), rather than only failing later when the resulting
-    value is dumped. `bin`/`ext`/`fixext` values are unaffected and are never validated, since they are not required
-    to hold text.
+    The MessagePack specification explicitly allows a `str` value (`fixstr`, `str 8`, `str 16`, `str 32`) to contain
+    a byte sequence that is not valid UTF-8, and expects a deserializer to hand the original bytes back unchanged.
+    This library follows that: `from_msgpack()` reads `str` bytes (object keys included) as-is, without validating
+    them, and `to_msgpack()` writes them back as-is, so such a value round-trips through `from_msgpack(to_msgpack(j))`
+    byte for byte. However, [`dump()`](../../api/basic_json/dump.md) still requires valid UTF-8 and throws
+    [`type_error.316`](../../home/exceptions.md#jsonexceptiontype_error316) for a value read this way, unless an
+    error handler is passed that replaces or ignores the ill-formed bytes.
 
 ??? example
 

docs/mkdocs/docs/features/binary_formats/ubjson.md

@@ -47,6 +47,12 @@ The library uses the following mapping from JSON values types to UBJSON types ac
 
       - strings with more than 9223372036854775807 bytes (theoretical)
 
+!!! warning "UTF-8 validation of string values and object keys"
+
+    UBJSON's required string encoding is UTF-8. `to_ubjson()` validates the bytes of every string value and object
+    key and throws [`type_error.316`](../../home/exceptions.md#jsonexceptiontype_error316) for ill-formed UTF-8, so
+    a value with such a string cannot be serialized in the first place.
+
 !!! info "Unused UBJSON markers"
 
     The following markers are not used in the conversion:
@@ -120,6 +126,15 @@ The library maps UBJSON types to JSON value types as follows:
 
     The mapping is **complete** in the sense that any UBJSON value can be converted to a JSON value.
 
+!!! warning "Ill-formed UTF-8 in string values and object keys"
+
+    UBJSON's required string encoding is UTF-8, but this is not enforced on read: `from_ubjson()` accepts a string
+    value or object key whose bytes are not valid UTF-8 and hands them back unchanged. However,
+    [`dump()`](../../api/basic_json/dump.md) still requires valid UTF-8 and throws
+    [`type_error.316`](../../home/exceptions.md#jsonexceptiontype_error316) for such a value, unless an error
+    handler is passed that replaces or ignores the ill-formed bytes. `to_ubjson()` is strict as well (see above), so
+    a value read this way cannot be written back to UBJSON.
+
 ??? example
 
     ```cpp

docs/mkdocs/docs/home/exceptions.md

@@ -340,8 +340,9 @@ An unexpected byte was read in a [binary format](../features/binary_formats/inde
 ### json.exception.parse_error.113
 
 A string could not be read from a [binary format](../features/binary_formats/index.md): either a value that is not a
-string was read where one was required (for instance as a map key), the string's length specification is invalid, or
-the string's bytes are not valid UTF-8.
+string was read where one was required (for instance as a map key), or the string's length specification is invalid.
+The bytes of a string itself are not checked for valid UTF-8 on read; see the ill-formed UTF-8 notes on the
+individual [binary format](../features/binary_formats/index.md) pages for how such a string is handled afterward.
 
 CBOR and MessagePack allow map keys of any type, but JSON object keys are always strings. Maps with keys of any other
 type (for instance integers or `null`) are therefore not supported; see the notes on
@@ -364,9 +365,6 @@ type (for instance integers or `null`) are therefore not supported; see the note
     ```
     [json.exception.parse_error.113] parse error at byte 3: syntax error while parsing BJData string: string length must not be negative
     ```
-    ```
-    [json.exception.parse_error.113] parse error at byte 3: syntax error while parsing CBOR string: invalid string: ill-formed UTF-8 byte
-    ```
 
 ### json.exception.parse_error.114
 

include/nlohmann/detail/conversions/from_json.hpp

@@ -354,22 +354,22 @@ void())
 }
 
 template < typename BasicJsonType, typename T, std::size_t... Idx >
-std::array<T, sizeof...(Idx)> from_json_inplace_array_impl(BasicJsonType&& j,
+std::array<T, sizeof...(Idx)> from_json_inplace_array_impl(const BasicJsonType& j,
                      identity_tag<std::array<T, sizeof...(Idx)>> /*unused*/, index_sequence<Idx...> /*unused*/)
 {
-    return { { std::forward<BasicJsonType>(j).at(Idx).template get<T>()... } };
+    return { { j.at(Idx).template get<T>()... } };
 }
 
 template < typename BasicJsonType, typename T, std::size_t N >
-auto from_json(BasicJsonType&& j, identity_tag<std::array<T, N>> tag)
--> decltype(from_json_inplace_array_impl(std::forward<BasicJsonType>(j), tag, make_index_sequence<N> {}))
+auto from_json(const BasicJsonType& j, identity_tag<std::array<T, N>> tag)
+-> decltype(from_json_inplace_array_impl(j, tag, make_index_sequence<N> {}))
 {
     if (JSON_HEDLEY_UNLIKELY(!j.is_array()))
     {
         JSON_THROW(type_error::create(302, concat("type must be array, but is ", j.type_name()), &j));
     }
 
-    return from_json_inplace_array_impl(std::forward<BasicJsonType>(j), tag, make_index_sequence<N> {});
+    return from_json_inplace_array_impl(j, tag, make_index_sequence<N> {});
 }
 
 template<typename BasicJsonType>
@@ -504,54 +504,54 @@ template<std::size_t PTagValue, typename BasicJsonType, typename... Types>
 using tuple_type = std::tuple < decltype(from_json_tuple_get_impl(std::declval<BasicJsonType>(), detail::identity_tag<Types> {}, detail::priority_tag<PTagValue> {}))... >;
 
 template<std::size_t PTagValue, typename... Args, typename BasicJsonType, std::size_t... Idx>
-tuple_type<PTagValue, BasicJsonType, Args...> from_json_tuple_impl_base(BasicJsonType&& j, index_sequence<Idx...> /*unused*/)
+tuple_type<PTagValue, const BasicJsonType&, Args...> from_json_tuple_impl_base(const BasicJsonType& j, index_sequence<Idx...> /*unused*/)
 {
-    return tuple_type<PTagValue, BasicJsonType, Args...>(from_json_tuple_get_impl(std::forward<BasicJsonType>(j).at(Idx), detail::identity_tag<Args> {}, detail::priority_tag<PTagValue> {})...);
+    return tuple_type<PTagValue, const BasicJsonType&, Args...>(from_json_tuple_get_impl(j.at(Idx), detail::identity_tag<Args> {}, detail::priority_tag<PTagValue> {})...);
 }
 
 template<std::size_t PTagValue, typename BasicJsonType>
-std::tuple<> from_json_tuple_impl_base(BasicJsonType& /*unused*/, index_sequence<> /*unused*/)
+std::tuple<> from_json_tuple_impl_base(const BasicJsonType& /*unused*/, index_sequence<> /*unused*/)
 {
     return {};
 }
 
 template < typename BasicJsonType, class A1, class A2 >
-std::pair<A1, A2> from_json_tuple_impl(BasicJsonType&& j, identity_tag<std::pair<A1, A2>> /*unused*/, priority_tag<0> /*unused*/)
+std::pair<A1, A2> from_json_tuple_impl(const BasicJsonType& j, identity_tag<std::pair<A1, A2>> /*unused*/, priority_tag<0> /*unused*/)
 {
-    return {std::forward<BasicJsonType>(j).at(0).template get<A1>(),
-            std::forward<BasicJsonType>(j).at(1).template get<A2>()};
+    return {j.at(0).template get<A1>(),
+            j.at(1).template get<A2>()};
 }
 
 template<typename BasicJsonType, typename A1, typename A2>
-inline void from_json_tuple_impl(BasicJsonType&& j, std::pair<A1, A2>& p, priority_tag<1> /*unused*/)
+inline void from_json_tuple_impl(const BasicJsonType& j, std::pair<A1, A2>& p, priority_tag<1> /*unused*/)
 {
-    p = from_json_tuple_impl(std::forward<BasicJsonType>(j), identity_tag<std::pair<A1, A2>> {}, priority_tag<0> {});
+    p = from_json_tuple_impl(j, identity_tag<std::pair<A1, A2>> {}, priority_tag<0> {});
 }
 
 template<typename BasicJsonType, typename... Args>
-std::tuple<Args...> from_json_tuple_impl(BasicJsonType&& j, identity_tag<std::tuple<Args...>> /*unused*/, priority_tag<2> /*unused*/)
+std::tuple<Args...> from_json_tuple_impl(const BasicJsonType& j, identity_tag<std::tuple<Args...>> /*unused*/, priority_tag<2> /*unused*/)
 {
-    static_assert(cxpr_and<cxpr_or<cxpr_not<std::is_reference<Args>>, is_compatible_reference_type<BasicJsonType, Args>>...>::value,
+    static_assert(cxpr_and<cxpr_or<cxpr_not<std::is_reference<Args>>, is_compatible_reference_type<const BasicJsonType&, Args>>...>::value,
                   "Can not return a tuple containing references to types not contained in a Json, try Json::get_to()");
-    return from_json_tuple_impl_base<1, Args...>(std::forward<BasicJsonType>(j), index_sequence_for<Args...> {});
+    return from_json_tuple_impl_base<1, Args...>(j, index_sequence_for<Args...> {});
 }
 
 template<typename BasicJsonType, typename... Args>
-inline void from_json_tuple_impl(BasicJsonType&& j, std::tuple<Args...>& t, priority_tag<3> /*unused*/)
+inline void from_json_tuple_impl(const BasicJsonType& j, std::tuple<Args...>& t, priority_tag<3> /*unused*/)
 {
-    t = from_json_tuple_impl_base<2, Args...>(std::forward<BasicJsonType>(j), index_sequence_for<Args...> {});
+    t = from_json_tuple_impl_base<2, Args...>(j, index_sequence_for<Args...> {});
 }
 
 template<typename BasicJsonType, typename TupleRelated>
-auto from_json(BasicJsonType&& j, TupleRelated&& t)
--> decltype(from_json_tuple_impl(std::forward<BasicJsonType>(j), std::forward<TupleRelated>(t), priority_tag<3> {}))
+auto from_json(const BasicJsonType& j, TupleRelated&& t)
+-> decltype(from_json_tuple_impl(j, std::forward<TupleRelated>(t), priority_tag<3> {}))
 {
     if (JSON_HEDLEY_UNLIKELY(!j.is_array()))
     {
         JSON_THROW(type_error::create(302, concat("type must be array, but is ", j.type_name()), &j));
     }
 
-    return from_json_tuple_impl(std::forward<BasicJsonType>(j), std::forward<TupleRelated>(t), priority_tag<3> {});
+    return from_json_tuple_impl(j, std::forward<TupleRelated>(t), priority_tag<3> {});
 }
 
 template < typename BasicJsonType, typename Key, typename Value, typename Compare, typename Allocator,
@@ -636,7 +636,7 @@ struct from_json_fn
 /// namespace to hold default `from_json` function
 /// to see why this is required:
 /// http://www.open-std.org/jtc1/sc22/wg21/docs/papers/2015/n4381.html
-namespace // NOLINT(cert-dcl59-cpp,fuchsia-header-anon-namespaces,google-build-namespaces)
+namespace // NOLINT(cert-dcl59-cpp,fuchsia-header-anon-namespaces,google-build-namespaces,misc-anonymous-namespace-in-header)
 {
 #endif
 JSON_INLINE_VARIABLE constexpr const auto& from_json = // NOLINT(misc-definitions-in-headers)

include/nlohmann/detail/conversions/to_json.hpp

@@ -547,7 +547,7 @@ struct to_json_fn
 /// namespace to hold default `to_json` function
 /// to see why this is required:
 /// http://www.open-std.org/jtc1/sc22/wg21/docs/papers/2015/n4381.html
-namespace // NOLINT(cert-dcl59-cpp,fuchsia-header-anon-namespaces,google-build-namespaces)
+namespace // NOLINT(cert-dcl59-cpp,fuchsia-header-anon-namespaces,google-build-namespaces,misc-anonymous-namespace-in-header)
 {
 #endif
 JSON_INLINE_VARIABLE constexpr const auto& to_json = // NOLINT(misc-definitions-in-headers)

include/nlohmann/detail/input/binary_reader.hpp

@@ -421,7 +421,7 @@ class binary_reader
     @brief Parses a C-style string from the BSON input.
     @param[in,out] result  A reference to the string variable where the read
                             string is to be stored.
-    @return `true` if the \x00-byte indicating the end of the string was
+    @return `true` if the \\x00-byte indicating the end of the string was
              encountered before the EOF; false` indicates an unexpected EOF.
     */
     bool get_bson_cstr(string_t& result)
@@ -451,7 +451,7 @@ class binary_reader
     @brief read a C-style string from contiguous input in one step
 
     @param[in,out] result  the string to append to
-    @return whether the string was read; if the input has no \x00-byte, nothing
+    @return whether the string was read; if the input has no \\x00-byte, nothing
             is read, and @ref get_bson_cstr reports the end of the input
     */
     bool get_bson_cstr_bulk(string_t& result, std::true_type /*bulk*/)
@@ -3212,8 +3212,8 @@ class binary_reader
         return enter_object(detail::unknown_size());
     }
 
-    // Note, no reader for UBJSON binary types is implemented because they do
-    // not exist
+    // Note, UBJSON has no binary type of its own; BJData, which shares this
+    // reader, decodes optimized 'B' arrays as binary in get_ubjson_array().
 
     bool get_ubjson_high_precision_number()
     {
@@ -3919,7 +3919,7 @@ class binary_reader
 #endif
     }
 
-    /*
+    /*!
     @brief read a number from the input
 
     @tparam NumberType the type of the number
@@ -3929,10 +3929,10 @@ class binary_reader
     @return whether conversion completed
 
     @note This function needs to respect the system's endianness, because
-          bytes in CBOR, MessagePack, and UBJSON are stored in network order
-          (big endian) and therefore need reordering on little endian systems.
-          On the other hand, BSON and BJData use little endian and should reorder
-          on big endian systems.
+          bytes in CBOR, MessagePack, UBJSON, and BON8 are stored in network
+          order (big endian) and therefore need reordering on little endian
+          systems. On the other hand, BSON and BJData use little endian and
+          should reorder on big endian systems.
     */
     template<typename NumberType, bool InputIsLittleEndian = false>
     bool get_number(const input_format_t format, NumberType& result)
@@ -4031,28 +4031,13 @@ class binary_reader
                     const NumberType len,
                     string_t& result)
     {
-        // get_bytes() appends to result, and CBOR indefinite-length strings
-        // collect all their chunks in the same result; validating only the
-        // newly read bytes keeps the check linear in the input size
-        const std::size_t old_size = result.size();
-        if (JSON_HEDLEY_UNLIKELY(!get_bytes(format, len, "string", result)))
-        {
-            return false;
-        }
-
-        // RFC 8949 (CBOR) §3.1 and the MessagePack/BSON/UBJSON specifications
-        // all require text strings to be valid UTF-8; reject anything else
-        // right here so malformed input is caught at decode time instead of
-        // only surfacing later as a type_error.316 when the value is dumped
-        // (which would defeat allow_exceptions=false / strict discarding).
-        if (JSON_HEDLEY_UNLIKELY(!is_valid_utf8(result, old_size)))
-        {
-            return sax->parse_error(chars_read, get_token_string(),
-                                    parse_error::create(113, chars_read,
-                                            exception_message(format, "invalid string: ill-formed UTF-8 byte", "string"), nullptr));
-        }
-
-        return true;
+        // Strings are taken as is: none of CBOR (RFC 8949 §3.1 leaves the
+        // choice to the decoder), MessagePack (whose spec explicitly allows
+        // a str object to contain an invalid byte sequence), UBJSON, BJData,
+        // or BSON requires a decoder to reject ill-formed UTF-8. The bytes
+        // are kept unchanged; dump() and the binary writers are the ones
+        // that check them and report type_error.316 if they are not valid.
+        return get_bytes(format, len, "string", result);
     }
 
     /*!

include/nlohmann/detail/input/input_adapters.hpp

@@ -8,12 +8,12 @@
 
 #pragma once
 
+#include <algorithm> // min
 #include <array> // array
 #include <cstddef> // size_t
+#include <cstdint> // uint32_t
 #include <cstring> // strlen
 #include <iterator> // begin, end, iterator_traits, random_access_iterator_tag, distance, next
-#include <memory> // shared_ptr, make_shared, addressof
-#include <numeric> // accumulate
 #include <streambuf> // streambuf
 #include <string> // string, char_traits
 #include <type_traits> // enable_if, is_base_of, is_pointer, is_integral, remove_pointer
@@ -28,6 +28,7 @@
 #include <nlohmann/detail/iterators/iterator_traits.hpp>
 #include <nlohmann/detail/macro_scope.hpp>
 #include <nlohmann/detail/meta/type_traits.hpp>
+#include <nlohmann/detail/string_utils.hpp>
 
 NLOHMANN_JSON_NAMESPACE_BEGIN
 namespace detail
@@ -82,8 +83,9 @@ class file_input_adapter
 };
 
 /*!
-Input adapter for a (caching) istream. Ignores a UFT Byte Order Mark at
-beginning of input. Does not support changing the underlying std::streambuf
+Input adapter for a (caching) istream. Does not skip a UTF Byte Order Mark
+itself; that is done by the lexer's skip_bom(). Does not support changing
+the underlying std::streambuf
 in mid-input. Maintains underlying std::istream and std::streambuf to support
 subsequent use of standard std::istream operations to process any input
 characters following those used in parsing the JSON input.  Clears the
@@ -454,32 +456,14 @@ struct wide_string_input_helper<BaseInputAdapter, 4>
             // get the current character
             const auto wc = input.get_character();
 
-            // UTF-32 to UTF-8 encoding
-            if (wc < 0x80)
+            if (wc <= 0x10FFFF)
             {
-                utf8_bytes[0] = static_cast<std::char_traits<char>::int_type>(wc);
-                utf8_bytes_filled = 1;
-            }
-            else if (wc <= 0x7FF)
-            {
-                utf8_bytes[0] = static_cast<std::char_traits<char>::int_type>(0xC0u | ((static_cast<unsigned int>(wc) >> 6u) & 0x1Fu));
-                utf8_bytes[1] = static_cast<std::char_traits<char>::int_type>(0x80u | (static_cast<unsigned int>(wc) & 0x3Fu));
-                utf8_bytes_filled = 2;
-            }
-            else if (wc <= 0xFFFF)
-            {
-                utf8_bytes[0] = static_cast<std::char_traits<char>::int_type>(0xE0u | ((static_cast<unsigned int>(wc) >> 12u) & 0x0Fu));
-                utf8_bytes[1] = static_cast<std::char_traits<char>::int_type>(0x80u | ((static_cast<unsigned int>(wc) >> 6u) & 0x3Fu));
-                utf8_bytes[2] = static_cast<std::char_traits<char>::int_type>(0x80u | (static_cast<unsigned int>(wc) & 0x3Fu));
-                utf8_bytes_filled = 3;
-            }
-            else if (wc <= 0x10FFFF)
-            {
-                utf8_bytes[0] = static_cast<std::char_traits<char>::int_type>(0xF0u | ((static_cast<unsigned int>(wc) >> 18u) & 0x07u));
-                utf8_bytes[1] = static_cast<std::char_traits<char>::int_type>(0x80u | ((static_cast<unsigned int>(wc) >> 12u) & 0x3Fu));
-                utf8_bytes[2] = static_cast<std::char_traits<char>::int_type>(0x80u | ((static_cast<unsigned int>(wc) >> 6u) & 0x3Fu));
-                utf8_bytes[3] = static_cast<std::char_traits<char>::int_type>(0x80u | (static_cast<unsigned int>(wc) & 0x3Fu));
-                utf8_bytes_filled = 4;
+                // UTF-32 to UTF-8 encoding
+                utf8_bytes_filled = 0;
+                encode_utf8(static_cast<std::uint32_t>(wc), [&utf8_bytes, &utf8_bytes_filled](std::uint32_t byte)
+                {
+                    utf8_bytes[utf8_bytes_filled++] = static_cast<std::char_traits<char>::int_type>(byte);
+                });
             }
             else
             {
@@ -516,24 +500,15 @@ struct wide_string_input_helper<BaseInputAdapter, 2>
             // get the current character
             const auto wc = input.get_character();
 
-            // UTF-16 to UTF-8 encoding
-            if (wc < 0x80)
+            if (0xD800 > wc || wc >= 0xE000)
             {
-                utf8_bytes[0] = static_cast<std::char_traits<char>::int_type>(wc);
-                utf8_bytes_filled = 1;
-            }
-            else if (wc <= 0x7FF)
-            {
-                utf8_bytes[0] = static_cast<std::char_traits<char>::int_type>(0xC0u | ((static_cast<unsigned int>(wc) >> 6u)));
-                utf8_bytes[1] = static_cast<std::char_traits<char>::int_type>(0x80u | (static_cast<unsigned int>(wc) & 0x3Fu));
-                utf8_bytes_filled = 2;
-            }
-            else if (0xD800 > wc || wc >= 0xE000)
-            {
-                utf8_bytes[0] = static_cast<std::char_traits<char>::int_type>(0xE0u | ((static_cast<unsigned int>(wc) >> 12u)));
-                utf8_bytes[1] = static_cast<std::char_traits<char>::int_type>(0x80u | ((static_cast<unsigned int>(wc) >> 6u) & 0x3Fu));
-                utf8_bytes[2] = static_cast<std::char_traits<char>::int_type>(0x80u | (static_cast<unsigned int>(wc) & 0x3Fu));
-                utf8_bytes_filled = 3;
+                // a UTF-16 code unit outside the surrogate range is a valid
+                // code point (at most U+FFFF) on its own
+                utf8_bytes_filled = 0;
+                encode_utf8(static_cast<std::uint32_t>(wc), [&utf8_bytes, &utf8_bytes_filled](std::uint32_t byte)
+                {
+                    utf8_bytes[utf8_bytes_filled++] = static_cast<std::char_traits<char>::int_type>(byte);
+                });
             }
             else
             {
@@ -551,11 +526,11 @@ struct wide_string_input_helper<BaseInputAdapter, 2>
                     if (0xDC00 <= wc2 && wc2 <= 0xDFFF)
                     {
                         const auto charcode = 0x10000u + (((static_cast<unsigned int>(wc) & 0x3FFu) << 10u) | (wc2 & 0x3FFu));
-                        utf8_bytes[0] = static_cast<std::char_traits<char>::int_type>(0xF0u | (charcode >> 18u));
-                        utf8_bytes[1] = static_cast<std::char_traits<char>::int_type>(0x80u | ((charcode >> 12u) & 0x3Fu));
-                        utf8_bytes[2] = static_cast<std::char_traits<char>::int_type>(0x80u | ((charcode >> 6u) & 0x3Fu));
-                        utf8_bytes[3] = static_cast<std::char_traits<char>::int_type>(0x80u | (charcode & 0x3Fu));
-                        utf8_bytes_filled = 4;
+                        utf8_bytes_filled = 0;
+                        encode_utf8(charcode, [&utf8_bytes, &utf8_bytes_filled](std::uint32_t byte)
+                        {
+                            utf8_bytes[utf8_bytes_filled++] = static_cast<std::char_traits<char>::int_type>(byte);
+                        });
                         valid_pair = true;
                     }
                 }
@@ -769,6 +744,9 @@ struct container_input_adapter_factory< ContainerType,
 
            static adapter_type create(ContainerType&& container)
 {
+    // container is forwarded twice on purpose: the resulting begin/end
+    // iterator types must match adapter_type, computed the same way
+    // NOLINTNEXTLINE(bugprone-use-after-move)
     return input_adapter(begin(std::forward<ContainerType>(container)), end(std::forward<ContainerType>(container)));
 }
        };
@@ -884,9 +862,9 @@ auto input_adapter(T (&array)[N]) -> decltype(input_adapter(array, array + N)) /
     return input_adapter(array, array + N);
 }
 
-// This class only handles inputs of input_buffer_adapter type.
-// It's required so that expressions like {ptr, len} can be implicitly cast
-// to the correct adapter.
+// This class only handles inputs that construct a contiguous_bytes_input_adapter
+// (e.g. span_input_adapter). It's required so that expressions like {ptr, len}
+// can be implicitly cast to the correct adapter.
 class span_input_adapter
 {
   public:

include/nlohmann/detail/input/json_sax.hpp

@@ -10,6 +10,7 @@
 
 #include <algorithm> // find_if, min
 #include <cstddef>
+#include <limits> // numeric_limits
 #include <string> // string
 #include <type_traits> // enable_if_t
 #include <utility> // move, pair
@@ -175,6 +176,88 @@ template<typename ArrayType>
 inline void reserve_array(ArrayType& /*arr*/, std::size_t /*len*/, priority_tag<0> /*unused*/)
 {}
 
+#if JSON_DIAGNOSTIC_POSITIONS
+/*!
+@brief set the diagnostic positions of a value the DOM SAX parsers just stored
+
+Shared by json_sax_dom_parser and json_sax_dom_callback_parser. basic_json
+befriends this struct, as the position members are private.
+*/
+struct diagnostic_positions
+{
+    /*!
+    @param[in,out] v  the value that was just parsed
+    @param[in] lexer  the lexer that read it, or nullptr to leave @a v alone
+    */
+    template<typename BasicJsonType, typename LexerType>
+    static void set_from_lexer(BasicJsonType& v, LexerType* lexer)
+    {
+        if (lexer)
+        {
+            // Lexer has read past the current field value, so set the end position to the current position.
+            // The start position will be set below based on the length of the string representation
+            // of the value.
+            v.end_position = lexer->get_position();
+
+            switch (v.type())
+            {
+                case value_t::boolean:
+                {
+                    // 4 and 5 are the string length of "true" and "false"
+                    v.start_position = v.end_position - (v.m_data.m_value.boolean ? 4 : 5);
+                    break;
+                }
+
+                case value_t::null:
+                {
+                    // 4 is the string length of "null"
+                    v.start_position = v.end_position - 4;
+                    break;
+                }
+
+                case value_t::string:
+                {
+                    // escape sequences make the token longer than the value it
+                    // parses to, so the start position cannot be derived from
+                    // the value; use the offset the lexer recorded instead
+                    v.start_position = lexer->get_token_start_position();
+                    break;
+                }
+
+                case value_t::discarded:
+                {
+                    // an object or array the callback of
+                    // json_sax_dom_callback_parser rejected has no position
+                    v.end_position = std::string::npos;
+                    v.start_position = v.end_position;
+                    break;
+                }
+
+                case value_t::binary:
+                case value_t::number_integer:
+                case value_t::number_unsigned:
+                case value_t::number_float:
+                {
+                    v.start_position = v.end_position - lexer->get_string().size();
+                    break;
+                }
+
+                case value_t::object:
+                case value_t::array:
+                {
+                    // object and array are handled in start_object() and start_array() handlers
+                    // skip setting the values here.
+                    break;
+                }
+                default: // LCOV_EXCL_LINE
+                    // Handle all possible types discretely, default handler should never be reached.
+                    JSON_ASSERT(false); // NOLINT(cert-dcl03-c,hicpp-static-assert,misc-static-assert) LCOV_EXCL_LINE
+            }
+        }
+    }
+};
+#endif
+
 /*!
 @brief SAX implementation to create a JSON value from SAX events
 
@@ -376,76 +459,6 @@ class json_sax_dom_parser
 
   private:
 
-#if JSON_DIAGNOSTIC_POSITIONS
-    void handle_diagnostic_positions_for_json_value(BasicJsonType& v)
-    {
-        if (m_lexer_ref)
-        {
-            // Lexer has read past the current field value, so set the end position to the current position.
-            // The start position will be set below based on the length of the string representation
-            // of the value.
-            v.end_position = m_lexer_ref->get_position();
-
-            switch (v.type())
-            {
-                case value_t::boolean:
-                {
-                    // 4 and 5 are the string length of "true" and "false"
-                    v.start_position = v.end_position - (v.m_data.m_value.boolean ? 4 : 5);
-                    break;
-                }
-
-                case value_t::null:
-                {
-                    // 4 is the string length of "null"
-                    v.start_position = v.end_position - 4;
-                    break;
-                }
-
-                case value_t::string:
-                {
-                    // escape sequences make the token longer than the value it
-                    // parses to, so the start position cannot be derived from
-                    // the value; use the offset the lexer recorded instead
-                    v.start_position = m_lexer_ref->get_token_start_position();
-                    break;
-                }
-
-                // As we handle the start and end positions for values created during parsing,
-                // we do not expect the following value type to be called. Regardless, set the positions
-                // in case this is created manually or through a different constructor. Exclude from lcov
-                // since the exact condition of this switch is esoteric.
-                // LCOV_EXCL_START
-                case value_t::discarded:
-                {
-                    v.end_position = std::string::npos;
-                    v.start_position = v.end_position;
-                    break;
-                }
-                // LCOV_EXCL_STOP
-                case value_t::binary:
-                case value_t::number_integer:
-                case value_t::number_unsigned:
-                case value_t::number_float:
-                {
-                    v.start_position = v.end_position - m_lexer_ref->get_string().size();
-                    break;
-                }
-                case value_t::object:
-                case value_t::array:
-                {
-                    // object and array are handled in start_object() and start_array() handlers
-                    // skip setting the values here.
-                    break;
-                }
-                default: // LCOV_EXCL_LINE
-                    // Handle all possible types discretely, default handler should never be reached.
-                    JSON_ASSERT(false); // NOLINT(cert-dcl03-c,hicpp-static-assert,misc-static-assert,-warnings-as-errors) LCOV_EXCL_LINE
-            }
-        }
-    }
-#endif
-
     /*!
     @invariant If the ref stack is empty, then the passed value will be the new
                root.
@@ -461,7 +474,7 @@ class json_sax_dom_parser
             root = BasicJsonType(std::forward<Value>(v));
 
 #if JSON_DIAGNOSTIC_POSITIONS
-            handle_diagnostic_positions_for_json_value(root);
+            diagnostic_positions::set_from_lexer(root, m_lexer_ref);
 #endif
 
             return &root;
@@ -474,7 +487,7 @@ class json_sax_dom_parser
             ref_stack.back()->m_data.m_value.array->emplace_back(std::forward<Value>(v));
 
 #if JSON_DIAGNOSTIC_POSITIONS
-            handle_diagnostic_positions_for_json_value(ref_stack.back()->m_data.m_value.array->back());
+            diagnostic_positions::set_from_lexer(ref_stack.back()->m_data.m_value.array->back(), m_lexer_ref);
 #endif
 
             return &(ref_stack.back()->m_data.m_value.array->back());
@@ -485,7 +498,7 @@ class json_sax_dom_parser
         *object_element = BasicJsonType(std::forward<Value>(v));
 
 #if JSON_DIAGNOSTIC_POSITIONS
-        handle_diagnostic_positions_for_json_value(*object_element);
+        diagnostic_positions::set_from_lexer(*object_element, m_lexer_ref);
 #endif
 
         return object_element;
@@ -674,7 +687,7 @@ class json_sax_dom_callback_parser
 
 #if JSON_DIAGNOSTIC_POSITIONS
                     // Set start/end positions for discarded object.
-                    handle_diagnostic_positions_for_json_value(*ref_stack.back());
+                    diagnostic_positions::set_from_lexer(*ref_stack.back(), m_lexer_ref);
 #endif
                 }
             }
@@ -790,7 +803,7 @@ class json_sax_dom_callback_parser
 
 #if JSON_DIAGNOSTIC_POSITIONS
                     // Set start/end positions for discarded array.
-                    handle_diagnostic_positions_for_json_value(*ref_stack.back());
+                    diagnostic_positions::set_from_lexer(*ref_stack.back(), m_lexer_ref);
 #endif
                 }
             }
@@ -843,72 +856,6 @@ class json_sax_dom_callback_parser
 
   private:
 
-#if JSON_DIAGNOSTIC_POSITIONS
-    void handle_diagnostic_positions_for_json_value(BasicJsonType& v)
-    {
-        if (m_lexer_ref)
-        {
-            // Lexer has read past the current field value, so set the end position to the current position.
-            // The start position will be set below based on the length of the string representation
-            // of the value.
-            v.end_position = m_lexer_ref->get_position();
-
-            switch (v.type())
-            {
-                case value_t::boolean:
-                {
-                    // 4 and 5 are the string length of "true" and "false"
-                    v.start_position = v.end_position - (v.m_data.m_value.boolean ? 4 : 5);
-                    break;
-                }
-
-                case value_t::null:
-                {
-                    // 4 is the string length of "null"
-                    v.start_position = v.end_position - 4;
-                    break;
-                }
-
-                case value_t::string:
-                {
-                    // escape sequences make the token longer than the value it
-                    // parses to, so the start position cannot be derived from
-                    // the value; use the offset the lexer recorded instead
-                    v.start_position = m_lexer_ref->get_token_start_position();
-                    break;
-                }
-
-                case value_t::discarded:
-                {
-                    v.end_position = std::string::npos;
-                    v.start_position = v.end_position;
-                    break;
-                }
-
-                case value_t::binary:
-                case value_t::number_integer:
-                case value_t::number_unsigned:
-                case value_t::number_float:
-                {
-                    v.start_position = v.end_position - m_lexer_ref->get_string().size();
-                    break;
-                }
-
-                case value_t::object:
-                case value_t::array:
-                {
-                    // object and array are handled in start_object() and start_array() handlers
-                    // skip setting the values here.
-                    break;
-                }
-                default: // LCOV_EXCL_LINE
-                    // Handle all possible types discretely, default handler should never be reached.
-                    JSON_ASSERT(false); // NOLINT(cert-dcl03-c,hicpp-static-assert,misc-static-assert,-warnings-as-errors) LCOV_EXCL_LINE
-            }
-        }
-    }
-#endif
-
     /// if there is a pending duplicate-key stash entry for this exact slot,
     /// remove it from the stash; if restore_value is true, the stashed
     /// previous value is moved back into the slot first (use this when the
@@ -1030,7 +977,7 @@ class json_sax_dom_callback_parser
         auto value = BasicJsonType(std::forward<Value>(v));
 
 #if JSON_DIAGNOSTIC_POSITIONS
-        handle_diagnostic_positions_for_json_value(value);
+        diagnostic_positions::set_from_lexer(value, m_lexer_ref);
 #endif
 
         // check callback

include/nlohmann/detail/input/lexer.hpp

@@ -10,6 +10,7 @@
 
 #include <array> // array
 #include <cstddef> // size_t
+#include <cstdint> // uint32_t
 #include <cstdio> // snprintf
 #include <initializer_list> // initializer_list
 #include <string> // char_traits, string
@@ -22,6 +23,7 @@
 #include <nlohmann/detail/input/string_scan.hpp>
 #include <nlohmann/detail/macro_scope.hpp>
 #include <nlohmann/detail/meta/type_traits.hpp>
+#include <nlohmann/detail/string_utils.hpp>
 
 NLOHMANN_JSON_NAMESPACE_BEGIN
 namespace detail
@@ -220,9 +222,9 @@ class lexer : public lexer_base<BasicJsonType>
     /////////////////////
 
     /*!
-    @brief get codepoint from 4 hex characters following `\u`
+    @brief get codepoint from 4 hex characters following `\\u`
 
-    For input "\u c1 c2 c3 c4" the codepoint is:
+    For input "\\u c1 c2 c3 c4" the codepoint is:
       (c1 * 0x1000) + (c2 * 0x0100) + (c3 * 0x0010) + c4
     = (c1 << 12) + (c2 << 8) + (c3 << 4) + (c4 << 0)
 
@@ -486,32 +488,10 @@ class lexer : public lexer_base<BasicJsonType>
                             JSON_ASSERT(0x00 <= codepoint && codepoint <= 0x10FFFF);
 
                             // translate codepoint into bytes
-                            if (codepoint < 0x80)
+                            encode_utf8(static_cast<std::uint32_t>(codepoint), [this](std::uint32_t byte)
                             {
-                                // 1-byte characters: 0xxxxxxx (ASCII)
-                                add(static_cast<char_int_type>(codepoint));
-                            }
-                            else if (codepoint <= 0x7FF)
-                            {
-                                // 2-byte characters: 110xxxxx 10xxxxxx
-                                add(static_cast<char_int_type>(0xC0u | (static_cast<unsigned int>(codepoint) >> 6u)));
-                                add(static_cast<char_int_type>(0x80u | (static_cast<unsigned int>(codepoint) & 0x3Fu)));
-                            }
-                            else if (codepoint <= 0xFFFF)
-                            {
-                                // 3-byte characters: 1110xxxx 10xxxxxx 10xxxxxx
-                                add(static_cast<char_int_type>(0xE0u | (static_cast<unsigned int>(codepoint) >> 12u)));
-                                add(static_cast<char_int_type>(0x80u | ((static_cast<unsigned int>(codepoint) >> 6u) & 0x3Fu)));
-                                add(static_cast<char_int_type>(0x80u | (static_cast<unsigned int>(codepoint) & 0x3Fu)));
-                            }
-                            else
-                            {
-                                // 4-byte characters: 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx
-                                add(static_cast<char_int_type>(0xF0u | (static_cast<unsigned int>(codepoint) >> 18u)));
-                                add(static_cast<char_int_type>(0x80u | ((static_cast<unsigned int>(codepoint) >> 12u) & 0x3Fu)));
-                                add(static_cast<char_int_type>(0x80u | ((static_cast<unsigned int>(codepoint) >> 6u) & 0x3Fu)));
-                                add(static_cast<char_int_type>(0x80u | (static_cast<unsigned int>(codepoint) & 0x3Fu)));
-                            }
+                                add(static_cast<char_int_type>(byte));
+                            });
 
                             break;
                         }
@@ -1409,45 +1389,30 @@ scan_number_done:
     */
     token_type convert_number(token_type number_type, std::size_t mantissa_end)
     {
-        // If the caller does not need the converted value (only whether the
-        // input is syntactically valid; see json_sax_acceptor/accept()), an
-        // unsigned/integer token can be reported without calling
-        // strtoull()/strtoll() at all, *provided* we can already tell from
-        // the digit count alone that the conversion cannot overflow 64 bits.
-        // Such tokens are always finite and are accepted unconditionally by
-        // the parser regardless of their actual value (parser::sax_parse_internal()
-        // never checks finiteness for value_unsigned/value_integer), so the
-        // classification below is all that is needed.
+        // accept() only needs to know whether the input is valid, so it sets
+        // discard_number_values (see json.hpp), and an integer token whose
+        // digit count shows that it fits is reported without calling
+        // convert_integer(). A number with up to 18 digits always fits into
+        // both std::uint64_t and std::int64_t (18 nines is about 1e18, below
+        // INT64_MAX, which is about 9.2e18). Longer tokens take the exact path
+        // below, including the fallback to floating point when the value does
+        // not fit.
         //
-        // A decimal number with up to 18 digits is always representable in
-        // both std::uint64_t and std::int64_t (18 nines is ~1e18, well below
-        // both UINT64_MAX ~1.8e19 and INT64_MAX ~9.2e18), so strtoull()/strtoll()
-        // could not have set errno to ERANGE for it. Numbers with more digits
-        // (rare in practice) fall through to the exact code below, unchanged,
-        // so their handling -- including reclassification to value_float when
-        // the value overflows 64 bits, and rejection when it is not even
-        // finite as a double -- is bit-for-bit identical to before this
-        // optimization.
+        // With a narrower number_unsigned_t/number_integer_t (e.g.
+        // std::uint32_t), the exact path would reclassify some of these tokens
+        // as (finite) floats, while this check reports integers. That does not
+        // change the result of accept(): it always parses through
+        // json_sax_acceptor, whose number callbacks discard their argument and
+        // return true, and the parser rejects neither integers nor finite
+        // floats. value_unsigned/value_integer are left unset here, so a caller
+        // that reads the converted value must not set discard_number_values.
         //
-        // Note this reasons about std::uint64_t/std::int64_t, not about
-        // number_unsigned_t/number_integer_t (BasicJsonType's own, possibly
-        // narrower, template parameters -- e.g. std::uint32_t). That is fine
-        // *only* because discard_number_values is exclusively set by
-        // accept() (see json.hpp), and accept() always parses through the
-        // library's own json_sax_acceptor -- never a user-supplied SAX
-        // consumer -- whose number_unsigned()/number_integer()/number_float()
-        // callbacks unconditionally discard their argument and return true.
-        // So for every caller that can reach this branch, neither the token
-        // classification below nor the eventual (possibly narrowed, and on
-        // this fast path left stale/unset) value_unsigned/value_integer is
-        // ever consulted -- an unsigned/integer token is accepted outright,
-        // and even a >18-digit token that this fast path deliberately falls
-        // through for is, once reclassified to value_float, still finite
-        // (and thus accepted) for any digit count that fits in number_unsigned_t
-        // or number_integer_t regardless of that type's width. If this
-        // function is ever taught to run with discard_number_values true for
-        // a caller that *does* read the converted value, this reasoning (and
-        // the fast path below) would need to be revisited.
+        // On contiguous input, scan_number_bulk_contiguous() converts integer
+        // tokens itself and does not pass them to this function, unless
+        // JSON_DIAGNOSTIC_POSITIONS is enabled. This check is therefore only
+        // reached for input without bulk access (e.g. streams), with
+        // JSON_DIAGNOSTIC_POSITIONS, or when scan_number_bulk_contiguous()
+        // falls back to scan_number().
         if (discard_number_values)
         {
             constexpr std::size_t safe_digit_count = 18;
@@ -1876,7 +1841,7 @@ scan_number_done:
         return value_float;
     }
 
-    /// return current string value (implicitly resets the token; useful only once)
+    /// return current string value
     string_t& get_string()
     {
         // a number token holds '.' regardless of the locale (#4084)
@@ -2178,11 +2143,11 @@ scan_number_done:
     /// the position of the decimal point in token_buffer
     std::size_t decimal_point_position = std::string::npos;
 
-    /// whether the caller (e.g. accept()/json_sax_acceptor) only needs the
-    /// token classification and never looks at the converted numeric value;
-    /// when set, scan_number() may skip strtoull()/strtoll() for
-    /// value_unsigned/value_integer tokens whose digit count guarantees they
-    /// fit into 64 bits (see scan_number())
+    /// whether the caller only needs the token types and never looks at the
+    /// converted numeric values; set only by accept(), which parses through
+    /// json_sax_acceptor. When set, convert_number() skips converting integer
+    /// tokens whose digit count guarantees that they fit into 64 bits (see
+    /// there)
     const bool discard_number_values = false;
 };
 

include/nlohmann/detail/input/parser.hpp

@@ -54,7 +54,8 @@ using parser_callback_t =
 /*!
 @brief syntax analysis
 
-This class implements a recursive descent parser.
+This class implements an iterative parser that keeps the open containers on
+an explicit stack and reports what it reads as SAX events.
 */
 template<typename BasicJsonType, typename InputAdapterType>
 class parser
@@ -98,28 +99,9 @@ class parser
         if (callback)
         {
             json_sax_dom_callback_parser<BasicJsonType, InputAdapterType> sdp(result, callback, allow_exceptions, &m_lexer);
-            sax_parse_internal(&sdp);
-
-            if (strict)
-            {
-                // in strict mode, input must be completely read
-                if (get_token() != token_type::end_of_input)
-                {
-                    sdp.parse_error(m_lexer.get_position(),
-                                    m_lexer.get_token_string(),
-                                    parse_error::create(101, m_lexer.get_position(),
-                                                        exception_message(token_type::end_of_input, "value"), nullptr));
-                }
-            }
-            else
-            {
-                // the caller keeps using the input: position it right after
-                // the value by leaving the character that terminated it
-                m_lexer.release_lookahead();
-            }
 
             // in case of an error, return a discarded value
-            if (sdp.is_errored())
+            if (!parse_dom(sdp, strict))
             {
                 result = value_t::discarded;
                 return;
@@ -135,26 +117,9 @@ class parser
         else
         {
             json_sax_dom_parser<BasicJsonType, InputAdapterType> sdp(result, allow_exceptions, &m_lexer);
-            sax_parse_internal(&sdp);
-
-            if (strict)
-            {
-                // in strict mode, input must be completely read
-                if (get_token() != token_type::end_of_input)
-                {
-                    sdp.parse_error(m_lexer.get_position(),
-                                    m_lexer.get_token_string(),
-                                    parse_error::create(101, m_lexer.get_position(), exception_message(token_type::end_of_input, "value"), nullptr));
-                }
-            }
-            else
-            {
-                // see above
-                m_lexer.release_lookahead();
-            }
 
             // in case of an error, return a discarded value
-            if (sdp.is_errored())
+            if (!parse_dom(sdp, strict))
             {
                 result = value_t::discarded;
                 return;
@@ -207,6 +172,46 @@ class parser
     }
 
   private:
+    /*!
+    @brief run a DOM SAX parser to completion and position the lexer
+
+    Shared by both branches of @ref parse(): builds no SAX parser itself,
+    but drives an already-constructed @a json_sax_dom_parser or
+    @ref json_sax_dom_callback_parser through @ref sax_parse_internal(),
+    then applies the strict-EOF check (reporting parse_error.101 through
+    @a sdp on failure) or, in non-strict mode, releases the lookahead so
+    the caller can keep reading the input right after the parsed value.
+
+    @param[in,out] sdp     the DOM SAX parser to run
+    @param[in] strict      whether to expect the last token to be EOF
+    @return whether @a sdp did not report an error
+    */
+    template<typename DomSax>
+    bool parse_dom(DomSax& sdp, const bool strict)
+    {
+        sax_parse_internal(&sdp);
+
+        if (strict)
+        {
+            // in strict mode, input must be completely read
+            if (get_token() != token_type::end_of_input)
+            {
+                sdp.parse_error(m_lexer.get_position(),
+                                m_lexer.get_token_string(),
+                                parse_error::create(101, m_lexer.get_position(),
+                                                    exception_message(token_type::end_of_input, "value"), nullptr));
+            }
+        }
+        else
+        {
+            // the caller keeps using the input: position it right after
+            // the value by leaving the character that terminated it
+            m_lexer.release_lookahead();
+        }
+
+        return !sdp.is_errored();
+    }
+
     template<typename SAX>
     JSON_HEDLEY_NON_NULL(2)
     bool sax_parse_internal(SAX* sax)
@@ -439,8 +444,9 @@ class parser
 
                     // We are done with this array. Before we can parse a
                     // new value, we need to evaluate the new state first.
-                    // By setting skip_to_state_evaluation to false, we
-                    // are effectively jumping to the beginning of this if.
+                    // By setting skip_to_state_evaluation to true, the next
+                    // iteration skips parsing a value and evaluates the
+                    // enclosing state directly.
                     JSON_ASSERT(!states.empty());
                     states.pop_back();
                     skip_to_state_evaluation = true;
@@ -500,8 +506,9 @@ class parser
 
                 // We are done with this object. Before we can parse a
                 // new value, we need to evaluate the new state first.
-                // By setting skip_to_state_evaluation to false, we
-                // are effectively jumping to the beginning of this if.
+                // By setting skip_to_state_evaluation to true, the next
+                // iteration skips parsing a value and evaluates the
+                // enclosing state directly.
                 JSON_ASSERT(!states.empty());
                 states.pop_back();
                 skip_to_state_evaluation = true;

include/nlohmann/detail/iterators/iter_impl.hpp

@@ -35,7 +35,7 @@ This class implements a both iterators (iterator and const_iterator) for the
       been set (e.g., by a constructor or a copy assignment). If the iterator is
       default-constructed, it is *uninitialized* and most methods are undefined.
       **The library uses assertions to detect calls on uninitialized iterators.**
-@requirement REQ-JSON-01 The class satisfies the following concept requirements:
+This class satisfies the following concept requirements (REQ-JSON-01):
 -
 [BidirectionalIterator](https://en.cppreference.com/w/cpp/named_req/BidirectionalIterator):
   The iterator that can be moved can be moved in both directions (i.e.

include/nlohmann/detail/iterators/iteration_proxy.hpp

@@ -213,11 +213,11 @@ namespace std
     JSON_HEDLEY_PRAGMA(clang diagnostic ignored "-Wmismatched-tags")
 #endif
 template<typename IteratorType>
-class tuple_size<::nlohmann::detail::iteration_proxy_value<IteratorType>> // NOLINT(cert-dcl58-cpp)
+class tuple_size<::nlohmann::detail::iteration_proxy_value<IteratorType>> // NOLINT(cert-dcl58-cpp,bugprone-std-namespace-modification)
     : public std::integral_constant<std::size_t, 2> {};
 
 template<std::size_t N, typename IteratorType>
-class tuple_element<N, ::nlohmann::detail::iteration_proxy_value<IteratorType >> // NOLINT(cert-dcl58-cpp)
+class tuple_element<N, ::nlohmann::detail::iteration_proxy_value<IteratorType >> // NOLINT(cert-dcl58-cpp,bugprone-std-namespace-modification)
 {
   public:
     using type = decltype(

include/nlohmann/detail/iterators/json_reverse_iterator.hpp

@@ -29,7 +29,7 @@ namespace detail
 iterator (to create @ref reverse_iterator) and @ref const_iterator (to
 create @ref const_reverse_iterator).
 
-@requirement REQ-JSON-02 The class satisfies the following concept requirements:
+This class satisfies the following concept requirements (REQ-JSON-02):
 -
 [BidirectionalIterator](https://en.cppreference.com/w/cpp/named_req/BidirectionalIterator):
   The iterator that can be moved can be moved in both directions (i.e.

include/nlohmann/detail/json_pointer.hpp

@@ -278,11 +278,11 @@ class json_pointer
             JSON_THROW(detail::out_of_range::create(404, detail::concat("unresolved reference token '", s, "'"), nullptr));
         }
 
-        // only triggered on special platforms (like 32bit), see also
-        // https://github.com/nlohmann/json/pull/2203
+        // the index does not fit into size_type; on 64-bit platforms this is
+        // only SIZE_MAX itself (see #2203 and #5395)
         if (res >= static_cast<unsigned long long>((std::numeric_limits<size_type>::max)()))  // NOLINT(runtime/int)
         {
-            JSON_THROW(detail::out_of_range::create(410, detail::concat("array index ", s, " exceeds size_type"), nullptr));   // LCOV_EXCL_LINE
+            JSON_THROW(detail::out_of_range::create(410, detail::concat("array index ", s, " exceeds size_type"), nullptr));
         }
 
         return static_cast<size_type>(res);
@@ -316,7 +316,7 @@ class json_pointer
     /*!
     @brief create and return a reference to the pointed to value
 
-    @complexity Linear in the number of reference tokens.
+    Complexity: Linear in the number of reference tokens.
 
     @throw parse_error.106 if an array index begins with '0'
     @throw parse_error.109 if array index is not a number
@@ -403,7 +403,7 @@ class json_pointer
 
     @return reference to the JSON value pointed to by the JSON pointer
 
-    @complexity Linear in the length of the JSON pointer.
+    Complexity: Linear in the length of the JSON pointer.
 
     @throw parse_error.106   if an array index begins with '0'
     @throw parse_error.109   if an array index was not a number

include/nlohmann/detail/macro_scope.hpp

@@ -195,13 +195,6 @@
     #define JSON_NO_THREAD_LOCAL 1
 #endif
 
-// disable documentation warnings on clang
-#if defined(__clang__)
-    #pragma clang diagnostic push
-    #pragma clang diagnostic ignored "-Wdocumentation"
-    #pragma clang diagnostic ignored "-Wdocumentation-unknown-command"
-#endif
-
 // allow disabling exceptions
 #if (defined(__cpp_exceptions) || defined(__EXCEPTIONS) || defined(_CPPUNWIND)) && !defined(JSON_NOEXCEPTION)
     #define JSON_THROW(exception) throw exception
@@ -260,7 +253,7 @@
     {                                                                                           \
         /* NOLINTNEXTLINE(modernize-type-traits) we use C++11 */                                \
         static_assert(std::is_enum<ENUM_TYPE>::value, #ENUM_TYPE " must be an enum!");          \
-        /* NOLINTNEXTLINE(modernize-avoid-c-arrays) we don't want to depend on <array> */       \
+        /* NOLINTNEXTLINE(cppcoreguidelines-avoid-c-arrays,hicpp-avoid-c-arrays,modernize-avoid-c-arrays) we don't want to depend on <array> */ \
         static const std::pair<ENUM_TYPE, BasicJsonType> m[] = __VA_ARGS__;                     \
         auto it = std::find_if(std::begin(m), std::end(m),                                      \
                                [e](const std::pair<ENUM_TYPE, BasicJsonType>& ej_pair) -> bool  \
@@ -274,7 +267,7 @@
     {                                                                                           \
         /* NOLINTNEXTLINE(modernize-type-traits) we use C++11 */                                \
         static_assert(std::is_enum<ENUM_TYPE>::value, #ENUM_TYPE " must be an enum!");          \
-        /* NOLINTNEXTLINE(modernize-avoid-c-arrays) we don't want to depend on <array> */       \
+        /* NOLINTNEXTLINE(cppcoreguidelines-avoid-c-arrays,hicpp-avoid-c-arrays,modernize-avoid-c-arrays) we don't want to depend on <array> */ \
         static const std::pair<ENUM_TYPE, BasicJsonType> m[] = __VA_ARGS__;                     \
         auto it = std::find_if(std::begin(m), std::end(m),                                      \
                                [&j](const std::pair<ENUM_TYPE, BasicJsonType>& ej_pair) -> bool \
@@ -313,7 +306,7 @@ void templated_json_throw(ExceptionType exception)
     {                                                                                           \
         /* NOLINTNEXTLINE(modernize-type-traits) we use C++11 */                                \
         static_assert(std::is_enum<ENUM_TYPE>::value, #ENUM_TYPE " must be an enum!");          \
-        /* NOLINTNEXTLINE(modernize-avoid-c-arrays) we don't want to depend on <array> */       \
+        /* NOLINTNEXTLINE(cppcoreguidelines-avoid-c-arrays,hicpp-avoid-c-arrays,modernize-avoid-c-arrays) we don't want to depend on <array> */ \
         static const std::pair<ENUM_TYPE, BasicJsonType> m[] = __VA_ARGS__;                     \
         auto it = std::find_if(std::begin(m), std::end(m),                                      \
                                [e](const std::pair<ENUM_TYPE, BasicJsonType>& ej_pair) -> bool  \
@@ -328,7 +321,7 @@ void templated_json_throw(ExceptionType exception)
     {                                                                                           \
         /* NOLINTNEXTLINE(modernize-type-traits) we use C++11 */                                \
         static_assert(std::is_enum<ENUM_TYPE>::value, #ENUM_TYPE " must be an enum!");          \
-        /* NOLINTNEXTLINE(modernize-avoid-c-arrays) we don't want to depend on <array> */       \
+        /* NOLINTNEXTLINE(cppcoreguidelines-avoid-c-arrays,hicpp-avoid-c-arrays,modernize-avoid-c-arrays) we don't want to depend on <array> */ \
         static const std::pair<ENUM_TYPE, BasicJsonType> m[] = __VA_ARGS__;                     \
         auto it = std::find_if(std::begin(m), std::end(m),                                      \
                                [&j](const std::pair<ENUM_TYPE, BasicJsonType>& ej_pair) -> bool \

include/nlohmann/detail/macro_unscope.hpp

@@ -8,11 +8,6 @@
 
 #pragma once
 
-// restore clang diagnostic settings
-#if defined(__clang__)
-    #pragma clang diagnostic pop
-#endif
-
 // clean up
 #undef JSON_ASSERT
 #undef JSON_INTERNAL_CATCH

include/nlohmann/detail/output/binary_writer.hpp

@@ -28,6 +28,7 @@
 #include <nlohmann/detail/macro_scope.hpp>
 #include <nlohmann/detail/output/output_adapters.hpp>
 #include <nlohmann/detail/string_concat.hpp>
+#include <nlohmann/detail/string_utils.hpp>
 
 NLOHMANN_JSON_NAMESPACE_BEGIN
 namespace detail
@@ -114,6 +115,8 @@ class binary_writer
 
     /*!
     @param[in] j  JSON value to serialize
+    @throw type_error.316 if a string value or an object key is not valid
+           UTF-8
     @throw type_error.317 if @a j is not an object
     */
     void write_bson(const BasicJsonType& j)
@@ -144,6 +147,8 @@ class binary_writer
 
     /*!
     @param[in] j  JSON value to serialize
+    @throw type_error.316 if a string value or an object key is not valid
+           UTF-8
     */
     void write_cbor(const BasicJsonType& j)
     {
@@ -210,6 +215,8 @@ class binary_writer
 
             case value_t::string:
             {
+                check_utf8(*j.m_data.m_value.string, j);
+
                 // step 1: write control byte and the string length
                 write_cbor_head(0x60, j.m_data.m_value.string->size());
 
@@ -286,6 +293,11 @@ class binary_writer
                 // step 2: write each element
                 for (const auto& el : *j.m_data.m_value.object)
                 {
+                    // el.first is checked here, against the object as
+                    // diagnostics context, because write_cbor(el.first)
+                    // converts it to a temporary basic_json that would be
+                    // used as the context instead
+                    check_utf8(el.first, j);
                     write_cbor(el.first);
                     write_cbor(el.second);
                 }
@@ -628,6 +640,8 @@ class binary_writer
     @param[in] add_prefix  whether prefixes need to be used for this value
     @param[in] use_bjdata  whether write in BJData format, default is false
     @param[in] bjdata_version  which BJData version to use, default is draft2
+    @throw type_error.316 if a string value or an object key is not valid
+           UTF-8
     */
     void write_ubjson(const BasicJsonType& j, const bool use_count,
                       const bool use_type, const bool add_prefix = true,
@@ -677,6 +691,8 @@ class binary_writer
 
             case value_t::string:
             {
+                check_utf8(*j.m_data.m_value.string, j);
+
                 if (add_prefix)
                 {
                     oa.write_character(to_char_type('S'));
@@ -839,6 +855,7 @@ class binary_writer
 
                 for (const auto& el : *j.m_data.m_value.object)
                 {
+                    check_utf8(el.first, j);
                     write_number_with_ubjson_prefix(el.first.size(), true, use_bjdata);
                     oa.write_characters(
                           reinterpret_cast<const CharType*>(el.first.data()),
@@ -883,6 +900,10 @@ class binary_writer
     /*!
     @return The size of a BSON document entry header, including the id marker
             and the entry name size (and its null-terminator).
+    @throw out_of_range.409 if @a name contains U+0000, before anything is
+           written
+    @throw type_error.316 if @a name is not valid UTF-8, before anything is
+           written
     */
     static std::size_t calc_bson_entry_header_size(const string_t& name, const BasicJsonType& j)
     {
@@ -892,7 +913,8 @@ class binary_writer
             JSON_THROW(out_of_range::create(409, concat("BSON key cannot contain code point U+0000 (at byte ", std::to_string(it), ")"), &j));
         }
 
-        static_cast<void>(j);
+        check_utf8(name, j);
+
         return /*id*/ 1ul + name.size() + /*zero-terminator*/1u;
     }
 
@@ -948,9 +970,21 @@ class binary_writer
 
     /*!
     @return The size of the BSON-encoded string in @a value
+    @throw type_error.316 if @a value is not valid UTF-8, before anything is
+           written
+
+    @note The UTF-8 check is skipped if @a value is already too long for the
+          32-bit BSON length field (@ref to_bson_length rejects it later, once
+          the size of the whole document is known); this also keeps the check
+          from reading past a StringType that reports a size larger than what
+          it actually holds.
     */
-    static std::size_t calc_bson_string_size(const string_t& value)
+    static std::size_t calc_bson_string_size(const string_t& value, const BasicJsonType& j)
     {
+        if (JSON_HEDLEY_LIKELY(value_in_range_of<std::int32_t>(value.size())))
+        {
+            check_utf8(value, j);
+        }
         return sizeof(std::int32_t) + value.size() + 1ul;
     }
 
@@ -1079,6 +1113,8 @@ class binary_writer
             is neither an object nor an array
     @throw out_of_range.415 if @a j is binary with a subtype that does not fit
            into a byte, before anything is written
+    @throw type_error.316 if @a j is a string that is not valid UTF-8, before
+           anything is written
     */
     static std::size_t calc_bson_value_size(const BasicJsonType& j)
     {
@@ -1100,7 +1136,7 @@ class binary_writer
                 return calc_bson_unsigned_size(j.m_data.m_value.number_unsigned);
 
             case value_t::string:
-                return calc_bson_string_size(*j.m_data.m_value.string);
+                return calc_bson_string_size(*j.m_data.m_value.string, j);
 
             case value_t::null:
                 return 0ul;
@@ -1213,6 +1249,8 @@ class binary_writer
            written
     @throw out_of_range.415 if a binary value's subtype does not fit into a
            byte, before anything is written
+    @throw type_error.316 if a string value or a key is not valid UTF-8,
+           before anything is written
     */
     static std::size_t calc_bson_sizes(const BasicJsonType& document, std::vector<std::size_t>& nested_sizes)
     {
@@ -2091,7 +2129,7 @@ class binary_writer
     */
     void write_bon8_string(const string_t& s, bool& string_open, const BasicJsonType& context)
     {
-        check_bon8_utf8(s, context);
+        check_utf8(s, context);
 
         // a string that follows another string terminates it
         if (string_open)
@@ -2121,27 +2159,17 @@ class binary_writer
     @throw type_error.316 if @a s is not valid UTF-8; the message names the
            first byte of the first invalid or incomplete sequence
     */
-    static void check_bon8_utf8(const string_t& s, const BasicJsonType& context)
+    static void check_utf8(const string_t& s, const BasicJsonType& context)
     {
         static_cast<void>(context); // only used when exceptions are enabled
         const auto* data = reinterpret_cast<const unsigned char*>(s.data());
         const std::size_t valid = valid_utf8_prefix(data, s.size());
         if (JSON_HEDLEY_UNLIKELY(valid != s.size()))
         {
-            JSON_THROW(type_error::create(316, concat("invalid UTF-8 byte at index ", std::to_string(valid), ": 0x", hex_byte(data[valid])), &context));
+            JSON_THROW(type_error::create(316, concat("invalid UTF-8 byte at index ", std::to_string(valid), ": 0x", detail::hex_byte(data[valid])), &context));
         }
     }
 
-    /// @return a byte as two uppercase hexadecimal digits
-    static std::string hex_byte(const std::uint8_t byte)
-    {
-        std::string result = "00";
-        constexpr const char* nibble_to_hex = "0123456789ABCDEF";
-        result[0] = nibble_to_hex[byte / 16];
-        result[1] = nibble_to_hex[byte % 16];
-        return result;
-    }
-
     /*!
     @brief write an integer in the shortest encoding
 

include/nlohmann/detail/output/output_adapters.hpp

@@ -8,11 +8,10 @@
 
 #pragma once
 
-#include <algorithm> // copy
 #include <cstddef> // size_t
-#include <iterator> // back_inserter
 #include <memory> // shared_ptr, make_shared
 #include <string> // basic_string
+#include <type_traits> // conditional, integral_constant, is_same
 #include <utility> // move
 #include <vector> // vector
 
@@ -31,6 +30,10 @@ namespace detail
 template<typename CharType> struct output_adapter_protocol
 {
     virtual void write_character(CharType c) = 0;
+    /// @param[in] s      pointer to the characters to write; binary_writer legitimately
+    ///                   passes a null pointer together with length 0 for an empty
+    ///                   string or binary value, so implementations must tolerate that
+    /// @param[in] length number of characters at @a s
     virtual void write_characters(const CharType* s, std::size_t length) = 0;
     virtual ~output_adapter_protocol() = default;
 
@@ -97,7 +100,6 @@ class output_vector_adapter : public output_adapter_protocol<CharType>
         sink.write_character(c);
     }
 
-    JSON_HEDLEY_NON_NULL(2)
     void write_characters(const CharType* s, std::size_t length) override
     {
         sink.write_characters(s, length);
@@ -117,12 +119,13 @@ class output_stream_adapter : public output_adapter_protocol<CharType>
         : stream(s)
     {}
 
+    // NOLINTNEXTLINE(portability-template-virtual-member-function)
     void write_character(CharType c) override
     {
         stream.put(c);
     }
 
-    JSON_HEDLEY_NON_NULL(2)
+    // NOLINTNEXTLINE(portability-template-virtual-member-function)
     void write_characters(const CharType* s, std::size_t length) override
     {
         stream.write(s, static_cast<std::streamsize>(length));
@@ -147,7 +150,6 @@ class output_string_adapter : public output_adapter_protocol<CharType>
         str.push_back(c);
     }
 
-    JSON_HEDLEY_NON_NULL(2)
     void write_characters(const CharType* s, std::size_t length) override
     {
         str.append(s, length);
@@ -190,7 +192,82 @@ class output_adapter_sink
     output_adapter_t<CharType> oa;
 };
 
-template<typename CharType, typename StringType = std::basic_string<CharType>>
+/// @brief whether std::basic_string<CharType> has a non-deprecated std::char_traits
+///        specialization, and is therefore usable as output_adapter's default StringType
+///
+/// std::char_traits is only guaranteed (and, on some standard libraries, only
+/// implemented without a deprecation warning) for the character types listed
+/// below; std::char_traits<T> for any other T (e.g. std::uint8_t, as used by the
+/// binary writers) is a non-standard extension some standard libraries deprecate.
+/// See https://github.com/nlohmann/json/issues/5725 item 2.
+template<typename CharType>
+struct is_output_adapter_string_char_type : std::integral_constant < bool,
+    std::is_same<CharType, char>::value ||
+    std::is_same<CharType, wchar_t>::value ||
+    std::is_same<CharType, char16_t>::value ||
+    std::is_same<CharType, char32_t>::value
+#if defined(__cpp_lib_char8_t) && (__cpp_lib_char8_t >= 201907L)
+    || std::is_same<CharType, char8_t>::value
+#endif
+    > {};
+
+/// @brief placeholder type for output_adapter's StringType and (with JSON_NO_IO
+///        undefined) its std::basic_ostream constructor parameter, for CharType
+///        with no non-deprecated std::char_traits specialization
+///
+/// Never actually used: the StringType- and std::basic_ostream-based
+/// output_adapter constructors are neither documented nor tested for such
+/// CharType (only the std::vector-based constructor is used for them, by the
+/// binary writers). Naming std::basic_string<CharType> or
+/// std::basic_ostream<CharType> anywhere such a constructor would otherwise be
+/// declared - even as an unused default template argument or an unused,
+/// never-called overload - instantiates std::char_traits<CharType> merely to
+/// name the type, which is exactly what triggers the deprecation warning this
+/// placeholder avoids.
+template<typename CharType>
+struct output_adapter_no_string_type {};
+
+// Select output_adapter's default StringType (and, below, its ostream
+// constructor's parameter type) via partial specialization, not
+// std::conditional: std::conditional<B, T, F> requires both T and F to be named
+// as template arguments up front, which would still instantiate (and thus name)
+// std::basic_string<CharType> / std::basic_ostream<CharType> for every CharType,
+// defeating the point. A bool non-type parameter with two specializations only
+// ever names the type that is actually selected.
+template<typename CharType, bool = is_output_adapter_string_char_type<CharType>::value>
+struct output_adapter_default_string_type
+{
+    using type = output_adapter_no_string_type<CharType>;
+};
+
+template<typename CharType>
+struct output_adapter_default_string_type<CharType, true>
+{
+    using type = std::basic_string<CharType>;
+};
+
+#ifndef JSON_NO_IO
+/// distinct from output_adapter_no_string_type, so the placeholder overloads of
+/// output_adapter's constructor (used when CharType is not a character type)
+/// stay distinct overloads instead of colliding into a single redeclaration
+template<typename CharType>
+struct output_adapter_no_ostream_type {};
+
+template<typename CharType, bool = is_output_adapter_string_char_type<CharType>::value>
+struct output_adapter_ostream_type
+{
+    using type = output_adapter_no_ostream_type<CharType>;
+};
+
+template<typename CharType>
+struct output_adapter_ostream_type<CharType, true>
+{
+    using type = std::basic_ostream<CharType>;
+};
+#endif  // JSON_NO_IO
+
+template < typename CharType, typename StringType =
+           typename output_adapter_default_string_type<CharType>::type >
 class output_adapter
 {
   public:
@@ -199,7 +276,7 @@ class output_adapter
         : oa(std::make_shared<output_vector_adapter<CharType, AllocatorType>>(vec)) {}
 
 #ifndef JSON_NO_IO
-    output_adapter(std::basic_ostream<CharType>& s)
+    output_adapter(typename output_adapter_ostream_type<CharType>::type& s)
         : oa(std::make_shared<output_stream_adapter<CharType>>(s)) {}
 #endif  // JSON_NO_IO
 

include/nlohmann/detail/output/serializer.hpp

@@ -3,24 +3,23 @@
 // |  |  |__   |  |  | | | |  version 3.12.0
 // |_____|_____|_____|_|___|  https://github.com/nlohmann/json
 //
-// SPDX-FileCopyrightText: 2008, 2009 Björn Hoehrmann <bjoern@hoehrmann.de>
 // SPDX-FileCopyrightText: 2013-2026 Niels Lohmann <https://nlohmann.me>
 // SPDX-License-Identifier: MIT
 
 #pragma once
 
-#include <algorithm> // reverse, remove, fill, find, none_of, min
+#include <algorithm> // remove, fill, find, none_of, min
 #include <array> // array
 #include <clocale> // localeconv, lconv
-#include <cmath> // labs, isfinite, isnan, signbit
+#include <cmath> // isfinite
 #include <cstddef> // size_t, ptrdiff_t
 #include <cstdint> // uint8_t
 #include <cstdio> // snprintf
 #include <cstring> // memcpy, memset
+#include <iterator> // next
 #include <limits> // numeric_limits
 #include <string> // string, char_traits
 #include <type_traits> // is_same
-#include <utility> // move
 #include <vector> // vector
 
 #include <nlohmann/detail/conversions/to_chars.hpp>
@@ -28,7 +27,6 @@
 #include <nlohmann/detail/input/string_scan.hpp>
 #include <nlohmann/detail/macro_scope.hpp>
 #include <nlohmann/detail/meta/cpp_future.hpp>
-#include <nlohmann/detail/output/binary_writer.hpp>
 #include <nlohmann/detail/output/output_adapters.hpp>
 #include <nlohmann/detail/recursion_depth_limit.hpp>
 #include <nlohmann/detail/string_concat.hpp>
@@ -67,7 +65,7 @@ class serializer
     @param[in] ichar  indentation character to use
     @param[in] pretty_print_  whether the output shall be pretty-printed
     @param[in] ensure_ascii_ If @a ensure_ascii_ is true, all non-ASCII
-    characters in the output are escaped with `\uXXXX` sequences, and the
+    characters in the output are escaped with `\\uXXXX` sequences, and the
     result consists of ASCII characters only.
     @param[in] indent_step_  the indent level
     @param[in] error_handler_  how to react on decoding errors
@@ -83,7 +81,6 @@ class serializer
                const std::size_t indent_step_ = 0,
                error_handler_t error_handler_ = error_handler_t::strict)
         : o(&s)
-        , locale(std::localeconv())
         , indent_char(ichar)
         , pretty_print(pretty_print_)
         , ensure_ascii(ensure_ascii_)
@@ -106,9 +103,10 @@ class serializer
     additional parameter. Arrays and objects are serialized without recursion,
     however deeply they are nested.
 
-    - strings and object keys are escaped using `escape_string()`
-    - integer numbers are converted implicitly via `operator<<`
-    - floating-point numbers are converted to a string using `"%g"` format
+    - strings and object keys are escaped using @ref dump_escaped
+    - integer numbers are converted using a digit-pair lookup table (@ref dump_integer)
+    - floating-point numbers are converted to a string using @ref dump_float, which
+      uses `to_chars` for IEEE-754 types and `snprintf` otherwise
     - binary values are serialized as objects containing the subtype and the
       byte array
 
@@ -283,127 +281,16 @@ class serializer
             }
 
             case value_t::string:
-            {
-                put_char('"');
-                dump_escaped(*val.m_data.m_value.string);
-                put_char('"');
-                return;
-            }
-
             case value_t::binary:
-            {
-                if (pretty_print)
-                {
-                    put_literal("{\n");
-
-                    // variable to hold indentation for recursive calls
-                    const auto new_indent = next_indent(current_indent, indent_step);
-
-                    put_indent(new_indent);
-
-                    put_literal("\"bytes\": [");
-
-                    if (!val.m_data.m_value.binary->empty())
-                    {
-                        for (auto i = val.m_data.m_value.binary->cbegin();
-                                i != val.m_data.m_value.binary->cend() - 1; ++i)
-                        {
-                            dump_byte(*i);
-                            put_literal(", ");
-                        }
-                        dump_byte(val.m_data.m_value.binary->back());
-                    }
-
-                    put_literal("],\n");
-                    put_indent(new_indent);
-
-                    put_literal("\"subtype\": ");
-                    if (val.m_data.m_value.binary->has_subtype())
-                    {
-                        dump_integer(val.m_data.m_value.binary->subtype());
-                    }
-                    else
-                    {
-                        put_literal("null");
-                    }
-                    put_char('\n');
-                    put_indent(current_indent);
-                    put_char('}');
-                }
-                else
-                {
-                    put_literal("{\"bytes\":[");
-
-                    if (!val.m_data.m_value.binary->empty())
-                    {
-                        for (auto i = val.m_data.m_value.binary->cbegin();
-                                i != val.m_data.m_value.binary->cend() - 1; ++i)
-                        {
-                            dump_byte(*i);
-                            put_char(',');
-                        }
-                        dump_byte(val.m_data.m_value.binary->back());
-                    }
-
-                    put_literal("],\"subtype\":");
-                    if (val.m_data.m_value.binary->has_subtype())
-                    {
-                        dump_integer(val.m_data.m_value.binary->subtype());
-                        put_char('}');
-                    }
-                    else
-                    {
-                        put_literal("null}");
-                    }
-                }
-                return;
-            }
-
             case value_t::boolean:
-            {
-                if (val.m_data.m_value.boolean)
-                {
-                    put_literal("true");
-                }
-                else
-                {
-                    put_literal("false");
-                }
-                return;
-            }
-
             case value_t::number_integer:
-            {
-                dump_integer(val.m_data.m_value.number_integer);
-                return;
-            }
-
             case value_t::number_unsigned:
-            {
-                dump_integer(val.m_data.m_value.number_unsigned);
-                return;
-            }
-
             case value_t::number_float:
-            {
-                dump_float(val.m_data.m_value.number_float);
-                return;
-            }
-
             case value_t::discarded:
-            {
-                put_literal("<discarded>");
-                return;
-            }
-
             case value_t::null:
-            {
-                put_literal("null");
+            default:
+                dump_scalar(val, current_indent);
                 return;
-            }
-
-            default:            // LCOV_EXCL_LINE
-                JSON_ASSERT(false); // NOLINT(cert-dcl03-c,hicpp-static-assert,misc-static-assert) LCOV_EXCL_LINE
         }
     }
 
@@ -560,9 +447,9 @@ class serializer
     @brief serialize the value @a val, but not the elements of a container
 
     An object or array with elements is opened and pushed onto @a stack for
-    @ref dump_internal to walk; everything else - including a binary value,
+    @ref dump_iteratively to walk; everything else - including a binary value,
     which looks like an object but has no elements to descend into - is written
-    out here in full.
+    out in full by @ref dump_scalar.
     */
     void dump_value(const BasicJsonType& val,
                     const std::size_t current_indent,
@@ -620,6 +507,35 @@ class serializer
                 return;
             }
 
+            case value_t::string:
+            case value_t::binary:
+            case value_t::boolean:
+            case value_t::number_integer:
+            case value_t::number_unsigned:
+            case value_t::number_float:
+            case value_t::discarded:
+            case value_t::null:
+            default:
+                dump_scalar(val, current_indent);
+                return;
+        }
+    }
+
+    /*!
+    @brief serialize the value @a val, which is neither an object nor an array
+
+    Shared by @ref dump_internal and @ref dump_value, so that a value is written
+    the same way however deeply it is nested. A binary value is written out here
+    in full: it looks like an object, but has no elements to descend into.
+
+    @param[in] val             value to serialize; not an object or array
+    @param[in] current_indent  the indentation of @a val, used for a
+                               pretty-printed binary value
+    */
+    void dump_scalar(const BasicJsonType& val, const std::size_t current_indent)
+    {
+        switch (val.m_data.m_type)
+        {
             case value_t::string:
             {
                 put_char('"');
@@ -740,6 +656,8 @@ class serializer
                 return;
             }
 
+            case value_t::object: // LCOV_EXCL_LINE
+            case value_t::array:  // LCOV_EXCL_LINE
             default:            // LCOV_EXCL_LINE
                 JSON_ASSERT(false); // NOLINT(cert-dcl03-c,hicpp-static-assert,misc-static-assert) LCOV_EXCL_LINE
         }
@@ -768,11 +686,11 @@ class serializer
     Escape a string by replacing certain special characters by a sequence of an
     escape character (backslash) and another character and other control
     characters by a sequence of "\u" followed by a four-digit hex
-    representation. The escaped string is written to output stream @a o.
+    representation. The escaped string is appended to @ref write_buffer.
 
     @param[in] s  the string to escape
 
-    @complexity Linear in the length of string @a s.
+    Complexity: Linear in the length of string @a s.
     */
     void dump_escaped(const string_t& s)
     {
@@ -962,7 +880,7 @@ class serializer
                     {
                         case error_handler_t::strict:
                         {
-                            JSON_THROW(type_error::create(316, concat("invalid UTF-8 byte at index ", std::to_string(i), ": 0x", hex_bytes(byte | 0)), nullptr));
+                            JSON_THROW(type_error::create(316, concat("invalid UTF-8 byte at index ", std::to_string(i), ": 0x", detail::hex_byte(byte)), nullptr));
                         }
 
                         case error_handler_t::ignore:
@@ -995,9 +913,9 @@ class serializer
                                 }
                                 else
                                 {
-                                    string_buffer[bytes++] = detail::binary_writer<BasicJsonType, char>::to_char_type('\xEF');
-                                    string_buffer[bytes++] = detail::binary_writer<BasicJsonType, char>::to_char_type('\xBF');
-                                    string_buffer[bytes++] = detail::binary_writer<BasicJsonType, char>::to_char_type('\xBD');
+                                    string_buffer[bytes++] = '\xEF';
+                                    string_buffer[bytes++] = '\xBF';
+                                    string_buffer[bytes++] = '\xBD';
                                 }
 
                                 // write buffer and reset index; there must be 13 bytes
@@ -1054,7 +972,7 @@ class serializer
             {
                 case error_handler_t::strict:
                 {
-                    JSON_THROW(type_error::create(316, concat("incomplete UTF-8 string; last byte: 0x", hex_bytes(static_cast<std::uint8_t>(s[s.size() - 1] | 0))), nullptr));
+                    JSON_THROW(type_error::create(316, concat("incomplete UTF-8 string; last byte: 0x", detail::hex_byte(static_cast<std::uint8_t>(s[s.size() - 1]))), nullptr));
                 }
 
                 case error_handler_t::ignore:
@@ -1276,21 +1194,7 @@ class serializer
     }
 
     /*!
-     * @brief convert a byte to a uppercase hex representation
-     * @param[in] byte byte to represent
-     * @return representation ("00".."FF")
-     */
-    static std::string hex_bytes(std::uint8_t byte)
-    {
-        std::string result = "FF";
-        constexpr const char* nibble_to_hex = "0123456789ABCDEF";
-        result[0] = nibble_to_hex[byte / 16];
-        result[1] = nibble_to_hex[byte % 16];
-        return result;
-    }
-
-    /*!
-     * @brief write a lowercase "\uXXXX" escape sequence into @a string_buffer
+     * @brief write a lowercase "\\uXXXX" escape sequence into @a string_buffer
      *
      * Branch-free replacement for `snprintf(buf, 7, "\\u%04x", codeunit)` in the
      * string escaping hot path. It writes exactly six characters ('\\', 'u' and
@@ -1402,7 +1306,7 @@ class serializer
     /*!
     @brief dump an integer
 
-    Dump a given integer to output stream @a o. Works internally with
+    Dump a given integer, appending it to @ref write_buffer. Works internally with
     @a number_buffer.
 
     @param[in] x  integer number (signed or unsigned) to dump
@@ -1439,7 +1343,7 @@ class serializer
         }
 
         // use a pointer to fill the buffer
-        auto buffer_ptr = number_buffer.begin(); // NOLINT(llvm-qualified-auto,readability-qualified-auto,cppcoreguidelines-pro-type-vararg,hicpp-vararg)
+        auto buffer_ptr = number_buffer.begin(); // NOLINT(llvm-qualified-auto,readability-qualified-auto)
 
         number_unsigned_t abs_value;
 
@@ -1493,7 +1397,7 @@ class serializer
     /*!
     @brief dump a floating-point number
 
-    Dump a given floating-point number to output stream @a o. Works internally
+    Dump a given floating-point number, appending it to @ref write_buffer. Works internally
     with @a number_buffer.
 
     @param[in] x  floating-point number to dump
@@ -1554,21 +1458,28 @@ class serializer
         // check if the buffer was large enough
         JSON_ASSERT(static_cast<std::size_t>(len) < number_buffer.size());
 
+        // look up the locale's thousands separator and decimal point now,
+        // matching what snprintf_float() just used (see lexer::get_decimal_point())
+        const auto* loc = std::localeconv();
+        JSON_ASSERT(loc != nullptr);
+        const char thousands_sep = (loc->thousands_sep == nullptr) ? '\0' : *loc->thousands_sep;
+        const char decimal_point = (loc->decimal_point == nullptr) ? '\0' : *loc->decimal_point;
+
         // erase thousands separators
-        if (locale.thousands_sep != '\0')
+        if (thousands_sep != '\0')
         {
             // NOLINTNEXTLINE(readability-qualified-auto,llvm-qualified-auto): std::remove returns an iterator, see https://github.com/nlohmann/json/issues/3081
-            const auto end = std::remove(number_buffer.begin(), number_buffer.begin() + len, locale.thousands_sep);
+            const auto end = std::remove(number_buffer.begin(), number_buffer.begin() + len, thousands_sep);
             std::fill(end, number_buffer.end(), '\0');
             JSON_ASSERT((end - number_buffer.begin()) <= len);
             len = (end - number_buffer.begin());
         }
 
         // convert decimal point to '.'
-        if (locale.decimal_point != '\0' && locale.decimal_point != '.')
+        if (decimal_point != '\0' && decimal_point != '.')
         {
             // NOLINTNEXTLINE(readability-qualified-auto,llvm-qualified-auto): std::find returns an iterator, see https://github.com/nlohmann/json/issues/3081
-            const auto dec_pos = std::find(number_buffer.begin(), number_buffer.end(), locale.decimal_point);
+            const auto dec_pos = std::find(number_buffer.begin(), number_buffer.end(), decimal_point);
             if (dec_pos != number_buffer.end())
             {
                 *dec_pos = '.';
@@ -1613,34 +1524,17 @@ class serializer
      */
     number_unsigned_t remove_sign(number_integer_t x) noexcept
     {
-        JSON_ASSERT(x < 0 && x < (std::numeric_limits<number_integer_t>::max)()); // NOLINT(misc-redundant-expression)
+        JSON_ASSERT(x < 0);
         return static_cast<number_unsigned_t>(-(x + 1)) + 1;
     }
 
   private:
-    /// the locale's thousand separator and decimal point characters
-    struct locale_chars
-    {
-        explicit locale_chars(const std::lconv* loc) noexcept
-            : thousands_sep(loc->thousands_sep == nullptr ? '\0' : std::char_traits<char>::to_char_type(* (loc->thousands_sep)))
-            , decimal_point(loc->decimal_point == nullptr ? '\0' : std::char_traits<char>::to_char_type(* (loc->decimal_point)))
-        {}
-
-        const char thousands_sep;
-        const char decimal_point;
-    };
-
     /// the output of the serializer (non-owning; the adapter lives at the call site)
     output_adapter_protocol<char>* o = nullptr;
 
     /// a (hopefully) large enough character buffer
     std::array<char, 64> number_buffer{{}};
 
-    /// computed once from std::localeconv() at construction; @ref
-    /// locale_chars keeps std::localeconv()'s pointer from having to be held
-    /// past the constructor, while still letting these stay const
-    const locale_chars locale;
-
     /// string buffer
     std::array<char, 512> string_buffer{{}};
 
@@ -1650,7 +1544,7 @@ class serializer
     /// whether to pretty-print the output
     const bool pretty_print;
 
-    /// whether to escape non-ASCII characters with \uXXXX sequences
+    /// whether to escape non-ASCII characters with \\uXXXX sequences
     const bool ensure_ascii;
 
     /// the indent level

include/nlohmann/detail/string_escape.hpp

@@ -62,8 +62,7 @@ inline StringType escape(const StringType& s)
 
 /*!
  * @brief string unescaping as described in RFC 6901 (Sect. 4)
- * @param[in] s string to unescape
- * @return    unescaped string
+ * @param[in,out] s string to unescape in place
  *
  * Note the order of escaping "~1" to "/" and "~0" to "~" is important.
  *

include/nlohmann/detail/string_utils.hpp

@@ -3,6 +3,7 @@
 // |  |  |__   |  |  | | | |  version 3.12.0
 // |_____|_____|_____|_|___|  https://github.com/nlohmann/json
 //
+// SPDX-FileCopyrightText: 2008, 2009 Björn Hoehrmann <bjoern@hoehrmann.de>
 // SPDX-FileCopyrightText: 2013-2026 Niels Lohmann <https://nlohmann.me>
 // SPDX-License-Identifier: MIT
 
@@ -36,6 +37,71 @@ StringType to_string(std::size_t value)
     return result;
 }
 
+/// @return a byte as two uppercase hexadecimal digits
+inline std::string hex_byte(const std::uint8_t byte)
+{
+    std::string result = "00";
+    constexpr const char* nibble_to_hex = "0123456789ABCDEF";
+    result[0] = nibble_to_hex[byte / 16];
+    result[1] = nibble_to_hex[byte % 16];
+    return result;
+}
+
+///////////////////
+// UTF-8 encoding //
+///////////////////
+
+/*!
+@brief encode a Unicode code point as UTF-8
+
+Used to turn a decoded code point back into bytes: by the wide-string input
+adapters in input_adapters.hpp (one code point per UTF-32 unit, per UTF-16
+unit outside the surrogate range, and per valid UTF-16 surrogate pair), and
+by the lexer's `\uXXXX`/`\uXXXX\uYYYY` handling in lexer.hpp. Passing a
+code point above U+10FFFF, or one in the surrogate range U+D800..U+DFFF, is
+undefined behavior; callers are expected to have rejected those already
+(the wide-string adapters pass malformed units through unencoded instead of
+calling this function, and the lexer rejects unpaired surrogates before
+reaching it).
+
+@tparam Out    a callable invoked with one byte (as std::uint32_t, 0x00..0xFF)
+               at a time, most significant byte first
+@param[in] cp   the code point to encode (at most U+10FFFF)
+@param[in] out  called once for each byte of the UTF-8 encoding of @a cp
+*/
+template<typename Out>
+void encode_utf8(std::uint32_t cp, Out&& out)
+{
+    JSON_ASSERT(cp <= 0x10FFFF);
+
+    if (cp < 0x80)
+    {
+        // 1-byte characters: 0xxxxxxx (ASCII)
+        out(cp);
+    }
+    else if (cp <= 0x7FF)
+    {
+        // 2-byte characters: 110xxxxx 10xxxxxx
+        out(0xC0u | (cp >> 6u));
+        out(0x80u | (cp & 0x3Fu));
+    }
+    else if (cp <= 0xFFFF)
+    {
+        // 3-byte characters: 1110xxxx 10xxxxxx 10xxxxxx
+        out(0xE0u | (cp >> 12u));
+        out(0x80u | ((cp >> 6u) & 0x3Fu));
+        out(0x80u | (cp & 0x3Fu));
+    }
+    else
+    {
+        // 4-byte characters: 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx
+        out(0xF0u | (cp >> 18u));
+        out(0x80u | ((cp >> 12u) & 0x3Fu));
+        out(0x80u | ((cp >> 6u) & 0x3Fu));
+        out(0x80u | (cp & 0x3Fu));
+    }
+}
+
 ///////////////////
 // UTF-8 decoding //
 ///////////////////
@@ -51,11 +117,24 @@ This is a single-byte step of a "shift-based" UTF-8 decoder originally
 written by Björn Hoehrmann. See
 http://bjoern.hoehrmann.de/utf-8/decoder/dfa/ for details.
 
-This decoder is the single source of truth for UTF-8 validation in this
-library: it is used both by the serializer (to escape and, in strict mode,
-reject ill-formed UTF-8 when dumping a string) and by the binary readers
-(to reject ill-formed UTF-8 in CBOR/MessagePack/BSON/UBJSON text strings at
-decode time; see @ref is_valid_utf8 below).
+The library checks UTF-8 well-formedness (RFC 3629, section 4) in three
+places, which differ in speed, diagnostics, and how they read the input:
+
+- decode() below: the serializer, to escape and, in strict mode, reject
+  ill-formed UTF-8 when dumping a string. The CBOR, MessagePack, BSON,
+  UBJSON and BJData readers do not use it: none of those specs requires a
+  decoder to reject ill-formed UTF-8 in text strings, so the readers keep
+  the bytes as is and leave the check to dump() and the binary writers.
+- the per-lead-byte switch in lexer::scan_string(): JSON text, with a
+  diagnostic for each kind of error.
+- validate_one_utf8() and valid_utf8_prefix() in string_scan.hpp: the lexer's
+  bulk string scan, the bulk path of the BON8 reader, and the BON8 writer.
+  They must accept exactly what the lexer's switch accepts.
+- the byte path of binary_reader::get_bon8_string(): BON8 input without bulk
+  access, and the bytes the bulk path leaves to it.
+
+All four must accept the same set of sequences, so a change to one needs a
+matching change to the others.
 
 @param[in,out] state  the current decoder state
 @param[in,out] codep  codepoint (valid only if resulting state is UTF8_ACCEPT)
@@ -100,38 +179,5 @@ inline std::uint8_t decode(std::uint8_t& state, std::uint32_t& codep, const std:
     return state;
 }
 
-/*!
-@brief check whether a string consists solely of valid UTF-8
-
-Used by the CBOR/MessagePack/BSON/UBJSON binary readers to reject text
-strings that are not valid UTF-8 at decode time (RFC 8949 §3.1 and the
-MessagePack/BSON specifications all require text strings to be UTF-8), so
-that malformed input is caught immediately instead of only surfacing later
-as a type_error.316 when the resulting value is dumped.
-
-@param[in] s      the string to check
-@param[in] first  index of the first byte to check; the bytes before it are
-                  assumed to have been validated already and to end on a
-                  code point boundary
-@return whether @a s (from index @a first on) is valid UTF-8
-*/
-template<typename StringType>
-inline bool is_valid_utf8(const StringType& s, const std::size_t first = 0) noexcept
-{
-    std::uint8_t state = UTF8_ACCEPT;
-    std::uint32_t codepoint = 0;
-
-    for (std::size_t i = first; i < s.size(); ++i)
-    {
-        decode(state, codepoint, static_cast<std::uint8_t>(s[i]));
-        if (state == UTF8_REJECT)
-        {
-            return false;
-        }
-    }
-
-    return state == UTF8_ACCEPT;
-}
-
 }  // namespace detail
 NLOHMANN_JSON_NAMESPACE_END

include/nlohmann/json.hpp

@@ -18,16 +18,6 @@
 #ifndef INCLUDE_NLOHMANN_JSON_HPP_
 #define INCLUDE_NLOHMANN_JSON_HPP_
 
-// Workaround for GCC template redefinition errors in C++ modules
-// When nlohmann/json.hpp is included in a C++20 module preamble after
-// other module imports, GCC may report spurious redefinition errors for
-// STL templates. These pragmas suppress those false positives.
-// See: https://github.com/nlohmann/json/issues/5103
-#if defined(__GNUC__) && !defined(__clang__) && __cplusplus >= 202002L
-    #pragma GCC diagnostic push
-    #pragma GCC diagnostic ignored "-Wignored-attributes"
-#endif
-
 #include <algorithm> // all_of, find, for_each, none_of
 #include <cmath> // isnan
 #include <cstddef> // nullptr_t, ptrdiff_t, size_t
@@ -164,6 +154,9 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
     friend class ::nlohmann::detail::json_sax_dom_parser;
     template<typename BasicJsonType, typename InputAdapterType>
     friend class ::nlohmann::detail::json_sax_dom_callback_parser;
+#if JSON_DIAGNOSTIC_POSITIONS
+    friend struct ::nlohmann::detail::diagnostic_positions;
+#endif
     friend class ::nlohmann::detail::exception;
 
     /// workaround type for MSVC
@@ -2548,12 +2541,12 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
 
     @throw what @ref json_serializer<ValueType> `from_json()` method throws
 
-    @liveexample{The example below shows several conversions from JSON values
+    The example below shows several conversions from JSON values
     to other types. There a few things to note: (1) Floating-point numbers can
-    be converted to integers\, (2) A JSON array can be converted to a standard
-    `std::vector<short>`\, (3) A JSON object can be converted to C++
-    associative containers such as `std::unordered_map<std::string\,
-    json>`.,get__ValueType_const}
+    be converted to integers, (2) A JSON array can be converted to a standard
+    `std::vector<short>`, (3) A JSON object can be converted to C++
+    associative containers such as `std::unordered_map<std::string,
+    json>`.
 
     @since version 2.1.0
     */
@@ -2620,7 +2613,7 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
 
     @return a copy of *this, converted into @a BasicJsonType
 
-    @complexity Depending on the implementation of the called `from_json()`
+    Complexity: Depending on the implementation of the called `from_json()`
                 method.
 
     @since version 3.2.0
@@ -2644,7 +2637,7 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
 
     @return a copy of *this
 
-    @complexity Constant.
+    Complexity: Constant.
 
     @since version 2.1.0
     */
@@ -2690,7 +2683,7 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
     @tparam ValueTypeCV the provided value type
     @tparam ValueType the returned value type
 
-    @return copy of the JSON value, converted to @tparam ValueType if necessary
+    @return copy of the JSON value, converted to @a ValueType if necessary
 
     @throw what @ref json_serializer<ValueType> `from_json()` method throws if conversion is required
 
@@ -2728,12 +2721,12 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
     @return pointer to the internally stored JSON value if the requested
     pointer type @a PointerType fits to the JSON value; `nullptr` otherwise
 
-    @complexity Constant.
+    Complexity: Constant.
 
-    @liveexample{The example below shows how pointers to internal values of a
+    The example below shows how pointers to internal values of a
     JSON value can be requested. Note that no type conversions are made and a
     `nullptr` is returned if the value and the requested pointer type does not
-    match.,get__PointerType}
+    match.
 
     @sa see @ref get_ptr() for explicit pointer-member access
 
@@ -2827,14 +2820,14 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
     to the JSON value type (e.g., the JSON value is of type boolean, but a
     string is requested); see example below
 
-    @complexity Linear in the size of the JSON value.
+    Complexity: Linear in the size of the JSON value.
 
-    @liveexample{The example below shows several conversions from JSON values
+    The example below shows several conversions from JSON values
     to other types. There a few things to note: (1) Floating-point numbers can
-    be converted to integers\, (2) A JSON array can be converted to a standard
-    `std::vector<short>`\, (3) A JSON object can be converted to C++
-    associative containers such as `std::unordered_map<std::string\,
-    json>`.,operator__ValueType}
+    be converted to integers, (2) A JSON array can be converted to a standard
+    `std::vector<short>`, (3) A JSON object can be converted to C++
+    associative containers such as `std::unordered_map<std::string,
+    json>`.
 
     @since version 1.0.0
     */
@@ -5289,6 +5282,19 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
     /// @deprecated This function is deprecated since 3.8.0 and will be removed in
     ///             version 4.0.0 of the library. Please use
     ///             sax_parse(ptr, ptr + len) instead.
+    //
+    // Clang reports "declaration is marked with '@deprecated' command but does
+    // not have a deprecation attribute" for this overload even though
+    // JSON_HEDLEY_DEPRECATED_FOR below does expand to __attribute__((deprecated));
+    // isolated reproductions of this exact declaration shape (doc comment,
+    // template<>, two stacked __attribute__ lines, an overload set of the same
+    // name) do not reproduce it, so this looks like a Clang comment/declaration
+    // association quirk specific to this overload within basic_json, not a
+    // genuine documentation bug. See #5725 item 2.
+#if defined(__clang__)
+#pragma clang diagnostic push
+#pragma clang diagnostic ignored "-Wdocumentation-deprecated-sync"
+#endif
     template <typename SAX>
     JSON_HEDLEY_DEPRECATED_FOR(3.8.0, sax_parse(ptr, ptr + len, ...))
     JSON_HEDLEY_NON_NULL(2)
@@ -5305,6 +5311,9 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
                // NOLINTNEXTLINE(hicpp-move-const-arg,performance-move-const-arg)
                : detail::binary_reader<basic_json, decltype(ia), SAX>(std::move(ia), format).sax_parse(sax, strict);
     }
+#if defined(__clang__)
+#pragma clang diagnostic pop
+#endif
 #ifndef JSON_NO_IO
     /// @brief deserialize from stream
     /// @sa https://json.nlohmann.me/api/basic_json/operator_gtgt/
@@ -6336,21 +6345,256 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
     {
         // the patch
         basic_json result(value_t::array);
+        diff_recursively(result, source, target, path, 0);
+        return result;
+    }
 
-        // if the values are the same, return an empty patch
+  private:
+    /// @brief two arrays or two objects @ref diff_iteratively is diffing
+    struct diff_frame
+    {
+        diff_frame(const basic_json* source_, const basic_json* target_, const std::size_t path_length_) noexcept
+            : source(source_), target(target_), path_length(path_length_)
+        {}
+
+        // declared for GCC's -Weffc++, which asks for them in a class with
+        // pointer members and a non-trivial destructor; the exception
+        // specifications are left implicit, as GCC 4.8 rejects explicit ones
+        // that differ from them
+        diff_frame(const diff_frame&) = default;
+        diff_frame(diff_frame&&) = default;
+        diff_frame& operator=(const diff_frame&) = default;
+        diff_frame& operator=(diff_frame&&) = default;
+        ~diff_frame() = default;
+
+        /// the values being diffed, both arrays or both objects
+        const basic_json* source;
+        const basic_json* target;
+        /// the length of their path in `current_path`
+        std::size_t path_length;
+        /// arrays: the next index to diff
+        std::size_t index = 0;
+        /// objects: the next member of source to look at
+        const_iterator member{}; // NOLINT(readability-redundant-member-init)
+        /// objects: the keys common to both, in source's order
+        std::vector<typename object_t::key_type> common_keys{}; // NOLINT(readability-redundant-member-init)
+        /// objects: the next entry of common_keys
+        std::size_t next_common = 0;
+        /// objects: the "add" operations for keys only target has
+        basic_json added_ops{}; // NOLINT(readability-redundant-member-init)
+    };
+
+    // The operations of a diff are built by the functions below rather than
+    // where they are needed: building one takes several temporaries, and
+    // unoptimized builds give each temporary a stack slot of its own in the
+    // function it appears in. In diff_recursively, which is on the call stack
+    // once per nesting level, that made every level cost kilobytes of stack.
+
+    /// @brief append a "replace" operation for @a path with @a value to @a result
+    static void diff_replace(basic_json& result, const string_t& path, const basic_json& value)
+    {
+        result.push_back(
+        {
+            {"op", "replace"}, {"path", path}, {"value", value}
+        });
+    }
+
+    /// @brief append a "remove" operation for @a path to @a result
+    static void diff_remove(basic_json& result, const string_t& path)
+    {
+        result.push_back(object(
+        {
+            {"op", "remove"}, {"path", path}
+        }));
+    }
+
+    /// @brief append an "add" operation for @a path with @a value to @a result
+    static void diff_add(basic_json& result, const string_t& path, const basic_json& value)
+    {
+        result.push_back(
+        {
+            {"op", "add"}, {"path", path}, {"value", value}
+        });
+    }
+
+    /// @brief append the "remove" operations for the elements of array
+    ///        @a source from @a index on, and the "add" operations for the
+    ///        elements of array @a target from source's size on, to @a result
+    static void diff_array_tails(basic_json& result, const basic_json& source, const basic_json& target,
+                                 const string_t& path, const std::size_t index)
+    {
+        // remove my remaining elements, highest index first; appending
+        // in that order avoids the quadratic reinsertion done before
+        for (std::size_t j = source.size(); j > index; --j)
+        {
+            diff_remove(result, detail::concat<string_t>(path, '/', detail::to_string<string_t>(j - 1)));
+        }
+
+        // add other remaining elements
+        for (std::size_t i = source.size(); i < target.size(); ++i)
+        {
+            diff_add(result, detail::concat<string_t>(path, "/-"), target[i]);
+        }
+    }
+
+    /*!
+    @brief compare the keys of objects @a source and @a target
+
+    If object_t does not keep its members in insertion order, or if the keys
+    both objects have are in the same order in both, and the keys only
+    @a target has come after them, stores the keys common to both in
+    source's order in @a common_keys, stores the "add" operations for the keys
+    only @a target has in @a added_ops, and returns true: the caller then diffs
+    the objects member by member. Otherwise, appends operations that remove
+    every member of @a source and add every member of @a target to @a result,
+    and returns false.
+    */
+    static bool diff_object_keys(basic_json& result, const basic_json& source, const basic_json& target,
+                                 const string_t& path, std::vector<typename object_t::key_type>& common_keys,
+                                 basic_json& added_ops)
+    {
+        // first pass: record, for every source key, whether it is
+        // common to both objects (in source's iteration order) or
+        // was deleted (i.e., in source but not in target) -- this is
+        // a by-product of the target.find() call already needed to
+        // tell the two cases apart, so it adds no extra lookups. The
+        // "remove" ops themselves are emitted later, interleaved
+        // with the per-key diffs in the caller's fast path, to match
+        // source's original iteration order (as the original,
+        // pre-reordering-aware implementation did) instead of
+        // grouping all removes before all per-key diffs.
+        std::vector<typename object_t::key_type> common_keys_source_order;
+        for (auto it = source.cbegin(); it != source.cend(); ++it)
+        {
+            if (target.find(it.key()) != target.end())
+            {
+                common_keys_source_order.push_back(it.key());
+            }
+        }
+
+        // second pass: find keys that were added (i.e., in target but
+        // not in source), and record the keys common to both, in
+        // target's iteration order -- again a by-product of the
+        // source.find() call already needed to detect added keys. At
+        // the same time, determine whether every added key comes
+        // after every common key in target's order (a precondition
+        // for the fast path, which only ever appends new keys
+        // at the very end). Both are only needed for an object_t that
+        // keeps its members in insertion order, such as the one
+        // backing `ordered_json`; for any other object_t, the fast
+        // path is always taken and they are not computed.
+        // The patch ops for keys that were added (i.e., in target but not
+        // in source) are built here so the fast path can reuse
+        // them without a second source.find() per target key. Only
+        // used by the fast path -- the slow (reordering) path
+        // rebuilds "add" ops for every key itself.
+        std::vector<typename object_t::key_type> common_keys_target_order;
+        bool new_keys_form_suffix = true;
+        bool seen_new_key = false;
+        for (auto it = target.cbegin(); it != target.cend(); ++it)
+        {
+            if (source.find(it.key()) == source.end())
+            {
+                seen_new_key = true;
+                diff_add(added_ops, detail::concat<string_t>(path, '/', detail::escape(it.key())), it.value());
+            }
+            else
+            {
+#ifdef JSON_HEDLEY_MSVC_VERSION
+#pragma warning(push )
+#pragma warning(disable : 4127) // ignore warning to replace if with if constexpr
+#endif
+                if (detail::is_ordered_map<object_t>::value)
+                {
+                    common_keys_target_order.push_back(it.key());
+                    if (seen_new_key)
+                    {
+                        new_keys_form_suffix = false;
+                    }
+                }
+#ifdef JSON_HEDLEY_MSVC_VERSION
+#pragma warning( pop )
+#endif
+            }
+        }
+
+        // Only an object type that keeps its members in insertion
+        // order, such as nlohmann::ordered_map, can need reordering:
+        // patch() appends a new member at the end of such an object.
+        // Any other object type places its members itself - std::map
+        // in key order, a hash map in an order its operator== ignores -
+        // so a member-by-member diff always reproduces target there.
+        if (!detail::is_ordered_map<object_t>::value
+                || (common_keys_source_order == common_keys_target_order && new_keys_form_suffix))
+        {
+            // fast path: order of common keys already matches (or the
+            // object_t's iteration order does not depend on
+            // insertion history), so a plain per-key diff is correct
+            // and minimal, as before
+            common_keys = std::move(common_keys_source_order);
+            return true;
+        }
+
+        // slow path: the common keys are in a different relative
+        // order in source and target (only possible for a
+        // reorderable object_t like ordered_map). Building a
+        // minimal reordering patch is a nontrivial (LCS-like)
+        // problem; instead, remove every source key -- both
+        // deleted keys (which must be removed regardless) and
+        // common keys (removed so they can be re-added in
+        // target's order) -- and re-add every key that should
+        // remain, with its final target value, in target's
+        // order. basic_json::patch()'s "add" operation on an
+        // object uses operator[], which appends at the end for a
+        // vector-backed insertion-ordered map when the key does
+        // not already exist -- so removing a key and then adding
+        // it moves it to the end, fixing its position.
+        for (auto it = source.cbegin(); it != source.cend(); ++it)
+        {
+            diff_remove(result, detail::concat<string_t>(path, '/', detail::escape(it.key())));
+        }
+
+        // add every key that is either common (just removed
+        // above) or brand new, in target's iteration order, so
+        // that the final order after applying the patch matches
+        // target exactly
+        for (auto it = target.cbegin(); it != target.cend(); ++it)
+        {
+            diff_add(result, detail::concat<string_t>(path, '/', detail::escape(it.key())), it.value());
+        }
+        return false;
+    }
+
+    /*!
+    @brief @ref diff, for values at nesting level @a depth, appending the
+           operations to @a result
+
+    Diffing two arrays or objects calls this function again, once per nesting
+    level, so values nested deeply enough used to exhaust the call stack and
+    terminate the process. The descent is bounded here: once @ref
+    detail::recursion_depth_limit levels have been entered, @ref
+    diff_iteratively diffs what is left without the call stack.
+    */
+    static void diff_recursively(basic_json& result, const basic_json& source, const basic_json& target,
+                                 const string_t& path, const std::size_t depth)
+    {
+        // if the values are the same, there is nothing to do
         if (source == target)
         {
-            return result;
+            return;
+        }
+
+        if (JSON_HEDLEY_UNLIKELY(depth >= detail::recursion_depth_limit()))
+        {
+            diff_iteratively(result, source, target, path);
+            return;
         }
 
         if (source.type() != target.type())
         {
             // different types: replace value
-            result.push_back(
-            {
-                {"op", "replace"}, {"path", path}, {"value", target}
-            });
-            return result;
+            diff_replace(result, path, target);
+            return;
         }
 
         switch (source.type())
@@ -6362,200 +6606,50 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
                 while (i < source.size() && i < target.size())
                 {
                     // recursive call to compare array values at index i
-                    auto temp_diff = diff(source[i], target[i], detail::concat<string_t>(path, '/', detail::to_string<string_t>(i)));
-                    result.insert(result.end(), temp_diff.begin(), temp_diff.end());
+                    diff_recursively(result, source[i], target[i], detail::concat<string_t>(path, '/', detail::to_string<string_t>(i)), depth + 1);
                     ++i;
                 }
 
                 // We now reached the end of at least one array
                 // in a second pass, traverse the remaining elements
-
-                // remove my remaining elements, highest index first; appending
-                // in that order avoids the quadratic reinsertion done before
-                for (std::size_t j = source.size(); j > i; --j)
-                {
-                    result.push_back(object(
-                    {
-                        {"op", "remove"},
-                        {"path", detail::concat<string_t>(path, '/', detail::to_string<string_t>(j - 1))}
-                    }));
-                }
-                i = source.size();
-
-                // add other remaining elements
-                while (i < target.size())
-                {
-                    result.push_back(
-                    {
-                        {"op", "add"},
-                        {"path", detail::concat<string_t>(path, "/-")},
-                        {"value", target[i]}
-                    });
-                    ++i;
-                }
-
+                diff_array_tails(result, source, target, path, i);
                 break;
             }
 
             case value_t::object:
             {
-                // first pass: record, for every source key, whether it is
-                // common to both objects (in source's iteration order) or
-                // was deleted (i.e., in source but not in target) -- this is
-                // a by-product of the target.find() call already needed to
-                // tell the two cases apart, so it adds no extra lookups. The
-                // "remove" ops themselves are emitted later, interleaved
-                // with the recursive per-key diffs in the fast path below,
-                // to match source's original iteration order (as the
-                // original, pre-reordering-aware implementation did) instead
-                // of grouping all removes before all recursive diffs.
-                std::vector<typename object_t::key_type> common_keys_source_order;
-                for (auto it = source.cbegin(); it != source.cend(); ++it)
-                {
-                    if (target.find(it.key()) != target.end())
-                    {
-                        common_keys_source_order.push_back(it.key());
-                    }
-                }
-
-                // second pass: find keys that were added (i.e., in target but
-                // not in source), and record the keys common to both, in
-                // target's iteration order -- again a by-product of the
-                // source.find() call already needed to detect added keys. At
-                // the same time, determine whether every added key comes
-                // after every common key in target's order (a precondition
-                // for the fast path below, which only ever appends new keys
-                // at the very end). Both are only needed for an object_t that
-                // keeps its members in insertion order, such as the one
-                // backing `ordered_json`; for any other object_t, the fast
-                // path is always taken and they are not computed.
-                // patch ops for keys that were added (i.e., in target but not
-                // in source); built here so the fast path below can reuse
-                // them without a second source.find() per target key. Only
-                // used by the fast path -- the slow (reordering) path
-                // rebuilds "add" ops for every key itself.
-                std::vector<typename object_t::key_type> common_keys_target_order;
+                std::vector<typename object_t::key_type> common_keys;
                 basic_json added_ops(value_t::array);
-                bool new_keys_form_suffix = true;
-                bool seen_new_key = false;
-                for (auto it = target.cbegin(); it != target.cend(); ++it)
+                if (diff_object_keys(result, source, target, path, common_keys, added_ops))
                 {
-                    if (source.find(it.key()) == source.end())
-                    {
-                        seen_new_key = true;
-                        const auto path_key = detail::concat<string_t>(path, '/', detail::escape(it.key()));
-                        added_ops.push_back(
-                        {
-                            {"op", "add"}, {"path", path_key},
-                            {"value", it.value()}
-                        });
-                    }
-                    else
-                    {
-#ifdef JSON_HEDLEY_MSVC_VERSION
-#pragma warning(push )
-#pragma warning(disable : 4127) // ignore warning to replace if with if constexpr
-#endif
-                        if (detail::is_ordered_map<object_t>::value)
-                        {
-                            common_keys_target_order.push_back(it.key());
-                            if (seen_new_key)
-                            {
-                                new_keys_form_suffix = false;
-                            }
-                        }
-#ifdef JSON_HEDLEY_MSVC_VERSION
-#pragma warning( pop )
-#endif
-                    }
-                }
-
-                // Only an object type that keeps its members in insertion
-                // order, such as nlohmann::ordered_map, can need reordering:
-                // patch() appends a new member at the end of such an object.
-                // Any other object type places its members itself - std::map
-                // in key order, a hash map in an order its operator== ignores -
-                // so a member-by-member diff always reproduces target there.
-                if (!detail::is_ordered_map<object_t>::value
-                        || (common_keys_source_order == common_keys_target_order && new_keys_form_suffix))
-                {
-                    // fast path: order of common keys already matches (or the
-                    // object_t's iteration order does not depend on
-                    // insertion history), so a plain per-key recursive diff
-                    // is correct and minimal, as before. common_keys_source_order
-                    // is, by construction, the subsequence of source's keys
-                    // that are common to both objects, in source's iteration
-                    // order -- so it can be walked in lockstep with `source`
-                    // using a cheap key comparison instead of another lookup.
-                    // Deleted keys (those source keys not in common_keys_source_order)
-                    // are interleaved here too, in source's original order, to
-                    // match the historical (pre-reordering-aware) output order.
-                    auto common_it = common_keys_source_order.cbegin();
+                    // fast path: common_keys is, by construction, the
+                    // subsequence of source's keys that are common to both
+                    // objects, in source's iteration order -- so it can be
+                    // walked in lockstep with `source` using a cheap key
+                    // comparison instead of another lookup. Deleted keys
+                    // (those source keys not in common_keys) are interleaved
+                    // here too, in source's original order, to match the
+                    // historical (pre-reordering-aware) output order.
+                    auto common_it = common_keys.cbegin();
                     for (auto it = source.cbegin(); it != source.cend(); ++it)
                     {
-                        if (common_it != common_keys_source_order.cend() && it.key() == *common_it)
+                        if (common_it != common_keys.cend() && it.key() == *common_it)
                         {
-                            const auto path_key = detail::concat<string_t>(path, '/', detail::escape(it.key()));
-                            auto temp_diff = diff(it.value(), target[it.key()], path_key);
-                            result.insert(result.end(), temp_diff.begin(), temp_diff.end());
+                            diff_recursively(result, it.value(), target[it.key()], detail::concat<string_t>(path, '/', detail::escape(it.key())), depth + 1);
                             ++common_it;
                         }
                         else
                         {
                             // found a key that is not in target -> remove it
-                            const auto path_key = detail::concat<string_t>(path, '/', detail::escape(it.key()));
-                            result.push_back(object(
-                            {
-                                {"op", "remove"}, {"path", path_key}
-                            }));
+                            diff_remove(result, detail::concat<string_t>(path, '/', detail::escape(it.key())));
                         }
                     }
 
-                    // append the "add" ops for brand-new keys collected above
-                    // during the pass over target -- no second source.find()
-                    // per target key needed
+                    // append the "add" ops for brand-new keys collected by
+                    // diff_object_keys -- no second source.find() per target
+                    // key needed
                     result.insert(result.end(), added_ops.begin(), added_ops.end());
                 }
-                else
-                {
-                    // slow path: the common keys are in a different relative
-                    // order in source and target (only possible for a
-                    // reorderable object_t like ordered_map). Building a
-                    // minimal reordering patch is a nontrivial (LCS-like)
-                    // problem; instead, remove every source key -- both
-                    // deleted keys (which must be removed regardless) and
-                    // common keys (removed so they can be re-added in
-                    // target's order) -- and re-add every key that should
-                    // remain, with its final target value, in target's
-                    // order. basic_json::patch()'s "add" operation on an
-                    // object uses operator[], which appends at the end for a
-                    // vector-backed insertion-ordered map when the key does
-                    // not already exist -- so removing a key and then adding
-                    // it moves it to the end, fixing its position.
-                    for (auto it = source.cbegin(); it != source.cend(); ++it)
-                    {
-                        const auto path_key = detail::concat<string_t>(path, '/', detail::escape(it.key()));
-                        result.push_back(object(
-                        {
-                            {"op", "remove"}, {"path", path_key}
-                        }));
-                    }
-
-                    // add every key that is either common (just removed
-                    // above) or brand new, in target's iteration order, so
-                    // that the final order after applying the patch matches
-                    // target exactly
-                    for (auto it = target.cbegin(); it != target.cend(); ++it)
-                    {
-                        const auto path_key = detail::concat<string_t>(path, '/', detail::escape(it.key()));
-                        result.push_back(
-                        {
-                            {"op", "add"}, {"path", path_key},
-                            {"value", it.value()}
-                        });
-                    }
-                }
-
                 break;
             }
 
@@ -6570,16 +6664,170 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
             default:
             {
                 // both primitive types: replace value
-                result.push_back(
-                {
-                    {"op", "replace"}, {"path", path}, {"value", target}
-                });
+                diff_replace(result, path, target);
                 break;
             }
         }
-
-        return result;
     }
+
+    /*!
+    @brief @ref diff without the call stack, appending the operations to
+           @a result
+
+    Produces the same operations as @ref diff_recursively. Only reached for
+    values nested more deeply than @ref detail::recursion_depth_limit.
+    */
+    static void diff_iteratively(basic_json& result, const basic_json& source, const basic_json& target,
+                                 const string_t& path)
+    {
+        // The arrays and objects being diffed are kept on an explicit stack,
+        // and every pair of elements is still diffed completely before the
+        // next one, so the operations come out in the same order as in
+        // diff_recursively. The path of the values being diffed is kept in
+        // one buffer that grows and shrinks with the stack, rather than in a
+        // new string per level.
+        std::vector<diff_frame> stack;
+        string_t current_path = path;
+
+        // diff `s` against `t`, whose path is current_path: primitives,
+        // values of different types, and objects whose members were reordered
+        // are handled right away; arrays and other objects get a frame
+        const auto enter = [&result, &stack, &current_path](const basic_json & s, const basic_json & t)
+        {
+            // if the values are the same, there is nothing to do. Arrays and
+            // objects are not compared up front: comparing them visits
+            // everything below them, so doing that at every level would take
+            // quadratic time in the nesting depth - equal ones yield no
+            // operations anyway.
+            if ((!s.is_structured() || !t.is_structured()) && s == t)
+            {
+                return;
+            }
+
+            if (s.type() != t.type())
+            {
+                // different types: replace value
+                diff_replace(result, current_path, t);
+                return;
+            }
+
+            switch (s.type())
+            {
+                case value_t::array:
+                {
+                    stack.emplace_back(&s, &t, current_path.size());
+                    return;
+                }
+
+                case value_t::object:
+                {
+                    std::vector<typename object_t::key_type> common_keys;
+                    basic_json added_ops(value_t::array);
+                    if (diff_object_keys(result, s, t, current_path, common_keys, added_ops))
+                    {
+                        // fast path: the frame walks source in lockstep with
+                        // common_keys, as diff_recursively does, and appends
+                        // added_ops once all members are done
+                        stack.emplace_back(&s, &t, current_path.size());
+                        stack.back().member = s.cbegin();
+                        stack.back().common_keys = std::move(common_keys);
+                        stack.back().added_ops = std::move(added_ops);
+                    }
+                    return;
+                }
+
+                case value_t::null:
+                case value_t::string:
+                case value_t::boolean:
+                case value_t::number_integer:
+                case value_t::number_unsigned:
+                case value_t::number_float:
+                case value_t::binary:
+                case value_t::discarded:
+                default:
+                {
+                    // both primitive types: replace value
+                    diff_replace(result, current_path, t);
+                    return;
+                }
+            }
+        };
+
+        enter(source, target);
+        while (!stack.empty())
+        {
+            // the frame is copied out member by member and changed through
+            // stack.back(): enter() may push a frame and the end of the loop
+            // pops it, either of which would invalidate a reference to it
+            const basic_json* const s = stack.back().source;
+            const basic_json* const t = stack.back().target;
+            const std::size_t path_length = stack.back().path_length;
+            const std::size_t depth = stack.size();
+
+            if (s->is_array())
+            {
+                const auto& source_array = *s->m_data.m_value.array;
+                const auto& target_array = *t->m_data.m_value.array;
+
+                // first pass: traverse common elements
+                const std::size_t i = stack.back().index;
+                if (i < source_array.size() && i < target_array.size())
+                {
+                    ++stack.back().index;
+                    detail::concat_into(current_path, '/', detail::to_string<string_t>(i));
+                    enter(source_array[i], target_array[i]);
+                    if (stack.size() == depth)
+                    {
+                        current_path.resize(path_length);
+                    }
+                    continue;
+                }
+
+                // We now reached the end of at least one array
+                // in a second pass, traverse the remaining elements
+                diff_array_tails(result, *s, *t, current_path, i);
+            }
+            else
+            {
+                const const_iterator it = stack.back().member;
+                if (it != s->cend())
+                {
+                    ++stack.back().member;
+                    const std::size_t next_common = stack.back().next_common;
+                    if (next_common < stack.back().common_keys.size() && it.key() == stack.back().common_keys[next_common])
+                    {
+                        ++stack.back().next_common;
+                        const basic_json& target_value = (*t)[it.key()];
+                        detail::concat_into(current_path, '/', detail::escape(it.key()));
+                        enter(it.value(), target_value);
+                        if (stack.size() == depth)
+                        {
+                            current_path.resize(path_length);
+                        }
+                    }
+                    else
+                    {
+                        // found a key that is not in target -> remove it
+                        diff_remove(result, detail::concat<string_t>(current_path, '/', detail::escape(it.key())));
+                    }
+                    continue;
+                }
+
+                // append the "add" ops for brand-new keys collected when the
+                // object was entered
+                result.insert(result.end(), stack.back().added_ops.begin(), stack.back().added_ops.end());
+            }
+
+            // this array or object is done: continue with the one it is in
+            stack.pop_back();
+            if (!stack.empty())
+            {
+                current_path.resize(stack.back().path_length);
+            }
+        }
+    }
+
+  public:
     /// @}
 
     ////////////////////////////////
@@ -6728,7 +6976,7 @@ namespace std // NOLINT(cert-dcl58-cpp)
 /// @brief hash value for JSON objects
 /// @sa https://json.nlohmann.me/api/basic_json/std_hash/
 NLOHMANN_BASIC_JSON_TPL_DECLARATION
-struct hash<nlohmann::NLOHMANN_BASIC_JSON_TPL> // NOLINT(cert-dcl58-cpp)
+struct hash<nlohmann::NLOHMANN_BASIC_JSON_TPL> // NOLINT(cert-dcl58-cpp,bugprone-std-namespace-modification)
 {
     std::size_t operator()(const nlohmann::NLOHMANN_BASIC_JSON_TPL& j) const
     {
@@ -6761,7 +7009,7 @@ struct less< ::nlohmann::detail::value_t> // do not remove the space after '<',
 /// @brief exchanges the values of two JSON objects
 /// @sa https://json.nlohmann.me/api/basic_json/std_swap/
 NLOHMANN_BASIC_JSON_TPL_DECLARATION
-inline void swap(nlohmann::NLOHMANN_BASIC_JSON_TPL& j1, nlohmann::NLOHMANN_BASIC_JSON_TPL& j2) noexcept(  // NOLINT(readability-inconsistent-declaration-parameter-name, cert-dcl58-cpp)
+inline void swap(nlohmann::NLOHMANN_BASIC_JSON_TPL& j1, nlohmann::NLOHMANN_BASIC_JSON_TPL& j2) noexcept(  // NOLINT(readability-inconsistent-declaration-parameter-name, cert-dcl58-cpp,bugprone-std-namespace-modification)
     is_nothrow_move_constructible<nlohmann::NLOHMANN_BASIC_JSON_TPL>::value&&                          // NOLINT(misc-redundant-expression,cppcoreguidelines-noexcept-swap,performance-noexcept-swap)
     is_nothrow_move_assignable<nlohmann::NLOHMANN_BASIC_JSON_TPL>::value)
 {
@@ -6775,7 +7023,7 @@ inline void swap(nlohmann::NLOHMANN_BASIC_JSON_TPL& j1, nlohmann::NLOHMANN_BASIC
 /// @brief std::formatter specialization for JSON values
 /// @sa https://json.nlohmann.me/api/basic_json/std_formatter/
 NLOHMANN_BASIC_JSON_TPL_DECLARATION
-struct formatter<nlohmann::NLOHMANN_BASIC_JSON_TPL, char> // NOLINT(cert-dcl58-cpp)
+struct formatter<nlohmann::NLOHMANN_BASIC_JSON_TPL, char> // NOLINT(cert-dcl58-cpp,bugprone-std-namespace-modification)
 {
     // -1 means compact output (dump()); any value >= 0 means pretty-printed
     // output with that many spaces (or indent_char) per level (dump(indent, indent_char)).
@@ -6855,11 +7103,6 @@ struct formatter<nlohmann::NLOHMANN_BASIC_JSON_TPL, char> // NOLINT(cert-dcl58-c
 // unit that includes this header.
 #include <nlohmann/detail/macro_unscope.hpp> // IWYU pragma: keep
 
-// End of GCC diagnostic pragmas for C++ modules support
-#if defined(__GNUC__) && !defined(__clang__) && __cplusplus >= 202002L
-    #pragma GCC diagnostic pop
-#endif
-
 // The user-defined string literals are in a separate header, because their
 // bodies instantiate the parser in every translation unit that includes them.
 // Define JSON_NO_AUTOMATIC_UDLS to include <nlohmann/json_literals.hpp> only

tests/CMakeLists.txt

@@ -10,7 +10,6 @@ set(JSON_32bitTest     AUTO CACHE STRING "Enable the 32bit unit test (ON/OFF/AUT
 set(JSON_TestStandards "" CACHE STRING "The list of standards to test explicitly.")
 
 # using an env var, since this will also affect targets executing cmake (such as "ci_test_compiler_default")
-set(JSON_FORCED_GLOBAL_COMPILE_OPTIONS $ENV{JSON_FORCED_GLOBAL_COMPILE_OPTIONS})
 if (NOT "" STREQUAL "$ENV{JSON_FORCED_GLOBAL_COMPILE_OPTIONS}")
     add_compile_options($ENV{JSON_FORCED_GLOBAL_COMPILE_OPTIONS})
 endif()
@@ -90,15 +89,20 @@ target_compile_options(test_main PUBLIC
     # https://github.com/nlohmann/json/pull/3229
     $<$<CXX_COMPILER_ID:Intel>:-diag-disable=2196>
 
-    $<$<NOT:$<CXX_COMPILER_ID:MSVC>>:-Wno-deprecated;-Wno-float-equal>
     $<$<CXX_COMPILER_ID:GNU>:-Wno-deprecated-declarations>
     $<$<CXX_COMPILER_ID:Intel>:-diag-disable=1786>)
+target_include_directories(test_main SYSTEM PUBLIC
+    thirdparty/doctest)
 target_include_directories(test_main PUBLIC
-    thirdparty/doctest
-    thirdparty/fifo_map
     ${PROJECT_BINARY_DIR}/include)
 target_link_libraries(test_main PUBLIC ${NLOHMANN_JSON_TARGET_NAME})
 
+# thirdparty/fifo_map is only used by the #972 regression test, so only
+# test-regression1 needs it on its include path (see json_test_set_test_options
+# below), rather than every test-* target via test_main.
+add_library(fifo_map_include INTERFACE)
+target_include_directories(fifo_map_include INTERFACE thirdparty/fifo_map)
+
 #############################################################################
 # define test- and standard-specific build settings
 #############################################################################
@@ -132,6 +136,9 @@ json_test_set_test_options(test-disabled_exceptions
 # raise timeout of expensive Unicode test
 json_test_set_test_options(test-unicode4 TEST_PROPERTIES TIMEOUT 3000)
 
+# only the #972 regression test needs thirdparty/fifo_map on its include path
+json_test_set_test_options(test-regression1 LINK_LIBRARIES fifo_map_include)
+
 #############################################################################
 # add unit tests
 #############################################################################

tests/abi/CMakeLists.txt

@@ -12,7 +12,6 @@ target_compile_options(abi_compat_common INTERFACE
     # https://github.com/nlohmann/json/pull/3229
     $<$<CXX_COMPILER_ID:Intel>:-diag-disable=2196>
 
-    $<$<NOT:$<CXX_COMPILER_ID:MSVC>>:-Wno-deprecated;-Wno-float-equal>
     $<$<CXX_COMPILER_ID:GNU>:-Wno-deprecated-declarations>
     $<$<CXX_COMPILER_ID:Intel>:-diag-disable=1786>)
 target_include_directories(abi_compat_common SYSTEM INTERFACE

tests/abi/config/config.hpp

@@ -28,7 +28,7 @@ std::string namespace_name(std::string ns, T* /*unused*/ = nullptr) // NOLINT(pe
     std::smatch m;
 
     // extract the true namespace name from the function signature
-    CAPTURE(ns);
+    CAPTURE(ns)
     CHECK(std::regex_search(ns, m, std::regex("nlohmann(::[a-zA-Z0-9_]+)*::basic_json")));
 
     return m.str();

tests/cmake_add_subdirectory/CMakeLists.txt

@@ -1,6 +1,8 @@
 add_test(NAME cmake_add_subdirectory_configure
   COMMAND ${CMAKE_COMMAND}
     -G "${CMAKE_GENERATOR}"
+    -A "${CMAKE_GENERATOR_PLATFORM}"
+    -T "${CMAKE_GENERATOR_TOOLSET}"
     -DCMAKE_CXX_COMPILER=${CMAKE_CXX_COMPILER}
     -DCMAKE_CXX_FLAGS=${CMAKE_CXX_FLAGS}
     -Dnlohmann_json_source=${PROJECT_SOURCE_DIR}

tests/cmake_fetch_content/CMakeLists.txt

@@ -1,21 +1,20 @@
-if (${CMAKE_VERSION} VERSION_GREATER "3.11.0")
-  add_test(NAME cmake_fetch_content_configure
-    COMMAND ${CMAKE_COMMAND}
+add_test(NAME cmake_fetch_content_configure
+  COMMAND ${CMAKE_COMMAND}
     -G "${CMAKE_GENERATOR}"
+    -A "${CMAKE_GENERATOR_PLATFORM}"
+    -T "${CMAKE_GENERATOR_TOOLSET}"
     -DCMAKE_CXX_COMPILER=${CMAKE_CXX_COMPILER}
     -DCMAKE_CXX_FLAGS=${CMAKE_CXX_FLAGS}
-    -Dnlohmann_json_source=${PROJECT_SOURCE_DIR}
     ${CMAKE_CURRENT_SOURCE_DIR}/project
-  )
-  add_test(NAME cmake_fetch_content_build
-    COMMAND ${CMAKE_COMMAND} --build .
-  )
-  set_tests_properties(cmake_fetch_content_configure PROPERTIES
-    FIXTURES_SETUP cmake_fetch_content
-    LABELS "git_required;not_reproducible"
-  )
-  set_tests_properties(cmake_fetch_content_build PROPERTIES
-    FIXTURES_REQUIRED cmake_fetch_content
-    LABELS "git_required;not_reproducible"
-  )
-endif()
+)
+add_test(NAME cmake_fetch_content_build
+  COMMAND ${CMAKE_COMMAND} --build .
+)
+set_tests_properties(cmake_fetch_content_configure PROPERTIES
+  FIXTURES_SETUP cmake_fetch_content
+  LABELS "git_required;not_reproducible"
+)
+set_tests_properties(cmake_fetch_content_build PROPERTIES
+  FIXTURES_REQUIRED cmake_fetch_content
+  LABELS "git_required;not_reproducible"
+)

tests/cmake_fetch_content/project/CMakeLists.txt

@@ -4,6 +4,14 @@ project(DummyImport CXX)
 
 include(FetchContent)
 
+# This test deliberately covers the pre-3.14 FetchContent_Populate pattern
+# (see FetchContent_MakeAvailable in ../../cmake_fetch_content2/project for
+# the 3.14+ alternative), which CMake 3.30 deprecated as CMP0169. Silence the
+# deprecation warning on purpose instead of switching to the new pattern.
+if(POLICY CMP0169)
+  cmake_policy(SET CMP0169 OLD)
+endif()
+
 get_filename_component(GIT_REPOSITORY_DIRECTORY ${CMAKE_CURRENT_SOURCE_DIR}/../../.. ABSOLUTE)
 FetchContent_Declare(json GIT_REPOSITORY ${GIT_REPOSITORY_DIRECTORY} GIT_TAG HEAD)
 

tests/cmake_fetch_content2/CMakeLists.txt

@@ -1,10 +1,11 @@
-if (${CMAKE_VERSION} VERSION_GREATER "3.14.0")
+if (${CMAKE_VERSION} VERSION_GREATER_EQUAL "3.14")
   add_test(NAME cmake_fetch_content2_configure
     COMMAND ${CMAKE_COMMAND}
     -G "${CMAKE_GENERATOR}"
+    -A "${CMAKE_GENERATOR_PLATFORM}"
+    -T "${CMAKE_GENERATOR_TOOLSET}"
     -DCMAKE_CXX_COMPILER=${CMAKE_CXX_COMPILER}
     -DCMAKE_CXX_FLAGS=${CMAKE_CXX_FLAGS}
-    -Dnlohmann_json_source=${PROJECT_SOURCE_DIR}
     ${CMAKE_CURRENT_SOURCE_DIR}/project
   )
   add_test(NAME cmake_fetch_content2_build

tests/cmake_import/CMakeLists.txt

@@ -2,6 +2,7 @@ add_test(NAME cmake_import_configure
   COMMAND ${CMAKE_COMMAND}
     -G "${CMAKE_GENERATOR}"
     -A "${CMAKE_GENERATOR_PLATFORM}"
+    -T "${CMAKE_GENERATOR_TOOLSET}"
     -DCMAKE_CXX_COMPILER=${CMAKE_CXX_COMPILER}
     -DCMAKE_CXX_FLAGS=${CMAKE_CXX_FLAGS}
     -Dnlohmann_json_DIR=${PROJECT_BINARY_DIR}

tests/cmake_import_minver/CMakeLists.txt

@@ -2,6 +2,7 @@ add_test(NAME cmake_import_minver_configure
   COMMAND ${CMAKE_COMMAND}
     -G "${CMAKE_GENERATOR}"
     -A "${CMAKE_GENERATOR_PLATFORM}"
+    -T "${CMAKE_GENERATOR_TOOLSET}"
     -DCMAKE_CXX_COMPILER=${CMAKE_CXX_COMPILER}
     -DCMAKE_CXX_FLAGS=${CMAKE_CXX_FLAGS}
     -Dnlohmann_json_DIR=${PROJECT_BINARY_DIR}

tests/cmake_target_include_directories/CMakeLists.txt

@@ -1,6 +1,8 @@
 add_test(NAME cmake_target_include_directories_configure
   COMMAND ${CMAKE_COMMAND}
     -G "${CMAKE_GENERATOR}"
+    -A "${CMAKE_GENERATOR_PLATFORM}"
+    -T "${CMAKE_GENERATOR_TOOLSET}"
     -DCMAKE_CXX_COMPILER=${CMAKE_CXX_COMPILER}
     -DCMAKE_CXX_FLAGS=${CMAKE_CXX_FLAGS}
     -Dnlohmann_json_source=${PROJECT_SOURCE_DIR}

tests/fuzzing.md

@@ -93,9 +93,10 @@ conventions:
   add it as a regression test to the unit test of the affected format (e.g., `tests/src/unit-bjdata.cpp`), with a
   comment naming the OSS-Fuzz issue. This way the input is checked by every CI run rather than only by OSS-Fuzz, and
   it stays covered even if OSS-Fuzz later closes the report as not reproducible.
-- **Keep the fuzzer drivers and the unit tests in sync.** The round-trip checks of the UBJSON and BJData drivers are
-  also run on a fixed corpus in the unit tests (see `tests/src/round_trip_corpus.hpp` and the "round-trip invariants"
-  test cases), so a regression shows up in CI first. When a driver's checks change, change the unit tests with them.
+- **Keep the fuzzer drivers and the unit tests in sync.** The round-trip checks of the BJData, BON8, BSON, CBOR,
+  MessagePack and UBJSON drivers are also run on a fixed corpus in the unit tests (see
+  `tests/src/round_trip_corpus.hpp` and the "round-trip invariants" test cases), so a regression shows up in CI
+  first. When a driver's checks change, change the unit tests with them.
 - **Record in the report whether the bug shipped.** OSS-Fuzz asks whether a crash was a short-lived regression or
   affects a released version; answer it when the fix is merged, as it decides whether the fix needs a release note or
   a security advisory (see the [security policy](../.github/SECURITY.md)).

tests/reports/2016-08-29-fuzz/index.html

@@ -1,10 +0,0 @@
-<table style="font-family: 'Trebuchet MS', 'Tahoma', 'Arial', 'Helvetica'">
-<tr><td style="width: 18ex"><b>Banner:</b></td><td>fuzz</td></tr>
-<tr><td><b>Directory:</b></td><td>fuzz-testing/out</td></tr>
-<tr><td><b>Generated on:</b></td><td>Mo 29 Aug 2016 22:14:22 CEST</td></tr>
-</table>
-<p>
-<img src="high_freq.png" width=1000 height=300><p>
-<img src="low_freq.png" width=1000 height=200><p>
-<img src="exec_speed.png" width=1000 height=200>
-

tests/reports/2016-09-09-nativejson_benchmark/README.md

@@ -1,31 +0,0 @@
-Results of the latest benchmark from <https://github.com/miloyip/nativejson-benchmark>.
-
-See <https://github.com/nlohmann/json/issues/307> for discussion.
-
-Original post at 2016-09-09 to <json@yahoogroups.com>:
-
-> Hi,
-> 
-> This benchmark evaluated conformance, parse/stringify speed/memory, and
-> code size. It can also be viewed as a long list of open source C/C++ JSON
-> libraries.
-> 
-> You can run the benchmark on your own machine by checkout this project.
-> 
-> https://github.com/miloyip/nativejson-benchmark
-> 
-> You can also view some sample results here:
-> 
-> https://rawgit.com/miloyip/nativejson-benchmark/master/sample/conformance.html
-> https://rawgit.com/miloyip/nativejson-benchmark/master/sample/performance_Corei7-4980HQ@2.80GHz_mac64_clang7.0.html
-> 
-> If you make a new library, you may use this for testing conformance and
-> performance. Afterwards, please submit a pull request.
-> 
-> Enjoy!
-> 
-> -- 
-> Milo Yip
-> 
-> https://github.com/miloyip/
-> http://twitter.com/miloyip/

tests/reports/2016-09-09-nativejson_benchmark/conformance_Nlohmann (C++11).md

@@ -1,670 +0,0 @@
-
-
-
-
-<!DOCTYPE html>
-<html lang="en" class="">
-  <head prefix="og: http://ogp.me/ns# fb: http://ogp.me/ns/fb# object: http://ogp.me/ns/object# article: http://ogp.me/ns/article# profile: http://ogp.me/ns/profile#">
-    <meta charset='utf-8'>
-    
-
-    <link crossorigin="anonymous" href="https://assets-cdn.github.com/assets/frameworks-3a71f36dec04358c4f2f42280fb2cf5c38856f935a3f609eab0a1ae31b1d635a.css" media="all" rel="stylesheet" />
-    <link crossorigin="anonymous" href="https://assets-cdn.github.com/assets/github-5c885e880e980dc7f119393287b84906d930ccaff83f6bff8ae2c086b87ca4d8.css" media="all" rel="stylesheet" />
-    
-    
-    <link crossorigin="anonymous" href="https://assets-cdn.github.com/assets/site-4ef7bbe907458c89cb1f7f5c5e6c4cd87e03acf66b1817325e644920d2a83330.css" media="all" rel="stylesheet" />
-    
-
-    <link as="script" href="https://assets-cdn.github.com/assets/frameworks-88471af1fec40ff9418efbe2ddd15b6896af8d772f8179004c254dffc25ea490.js" rel="preload" />
-    
-    <link as="script" href="https://assets-cdn.github.com/assets/github-e18e11a943ff2eb9394c72d4ec8b76592c454915b5839ae177d422777a046e29.js" rel="preload" />
-
-    <meta http-equiv="X-UA-Compatible" content="IE=edge">
-    <meta http-equiv="Content-Language" content="en">
-    <meta name="viewport" content="width=device-width">
-    
-    <title>nativejson-benchmark/conformance_Nlohmann (C++11).md at master · miloyip/nativejson-benchmark · GitHub</title>
-    <link rel="search" type="application/opensearchdescription+xml" href="/opensearch.xml" title="GitHub">
-    <link rel="fluid-icon" href="https://github.com/fluidicon.png" title="GitHub">
-    <link rel="apple-touch-icon" href="/apple-touch-icon.png">
-    <link rel="apple-touch-icon" sizes="57x57" href="/apple-touch-icon-57x57.png">
-    <link rel="apple-touch-icon" sizes="60x60" href="/apple-touch-icon-60x60.png">
-    <link rel="apple-touch-icon" sizes="72x72" href="/apple-touch-icon-72x72.png">
-    <link rel="apple-touch-icon" sizes="76x76" href="/apple-touch-icon-76x76.png">
-    <link rel="apple-touch-icon" sizes="114x114" href="/apple-touch-icon-114x114.png">
-    <link rel="apple-touch-icon" sizes="120x120" href="/apple-touch-icon-120x120.png">
-    <link rel="apple-touch-icon" sizes="144x144" href="/apple-touch-icon-144x144.png">
-    <link rel="apple-touch-icon" sizes="152x152" href="/apple-touch-icon-152x152.png">
-    <link rel="apple-touch-icon" sizes="180x180" href="/apple-touch-icon-180x180.png">
-    <meta property="fb:app_id" content="1401488693436528">
-
-      <meta content="https://avatars2.githubusercontent.com/u/1195774?v=3&amp;s=400" name="twitter:image:src" /><meta content="@github" name="twitter:site" /><meta content="summary" name="twitter:card" /><meta content="miloyip/nativejson-benchmark" name="twitter:title" /><meta content="nativejson-benchmark - C/C++ JSON parser/generator benchmark" name="twitter:description" />
-      <meta content="https://avatars2.githubusercontent.com/u/1195774?v=3&amp;s=400" property="og:image" /><meta content="GitHub" property="og:site_name" /><meta content="object" property="og:type" /><meta content="miloyip/nativejson-benchmark" property="og:title" /><meta content="https://github.com/miloyip/nativejson-benchmark" property="og:url" /><meta content="nativejson-benchmark - C/C++ JSON parser/generator benchmark" property="og:description" />
-      <meta name="browser-stats-url" content="https://api.github.com/_private/browser/stats">
-    <meta name="browser-errors-url" content="https://api.github.com/_private/browser/errors">
-    <link rel="assets" href="https://assets-cdn.github.com/">
-    
-    <meta name="pjax-timeout" content="1000">
-    
-    <meta name="request-id" content="D4563DA7:75ED:525C921:57D6FEBB" data-pjax-transient>
-
-    <meta name="msapplication-TileImage" content="/windows-tile.png">
-    <meta name="msapplication-TileColor" content="#ffffff">
-    <meta name="selected-link" value="repo_source" data-pjax-transient>
-
-    <meta name="google-site-verification" content="KT5gs8h0wvaagLKAVWq8bbeNwnZZK1r1XQysX3xurLU">
-<meta name="google-site-verification" content="ZzhVyEFwb7w3e0-uOTltm8Jsck2F5StVihD0exw2fsA">
-    <meta name="google-analytics" content="UA-3769691-2">
-
-<meta content="collector.githubapp.com" name="octolytics-host" /><meta content="github" name="octolytics-app-id" /><meta content="D4563DA7:75ED:525C921:57D6FEBB" name="octolytics-dimension-request_id" />
-<meta content="/&lt;user-name&gt;/&lt;repo-name&gt;/blob/show" data-pjax-transient="true" name="analytics-location" />
-
-
-
-  <meta class="js-ga-set" name="dimension1" content="Logged Out">
-
-
-
-        <meta name="hostname" content="github.com">
-    <meta name="user-login" content="">
-
-        <meta name="expected-hostname" content="github.com">
-      <meta name="js-proxy-site-detection-payload" content="N2RkMmY1ZjE1MTA4MzRhYTA5NDNkMjliNDU3OTA3ZTdlMGNmNDZjN2QyODBiZjM3MmYzMjFjNzY1ZjIwNjY4NHx7InJlbW90ZV9hZGRyZXNzIjoiMjEyLjg2LjYxLjE2NyIsInJlcXVlc3RfaWQiOiJENDU2M0RBNzo3NUVEOjUyNUM5MjE6NTdENkZFQkIiLCJ0aW1lc3RhbXAiOjE0NzM3MDc3MDh9">
-
-
-      <link rel="mask-icon" href="https://assets-cdn.github.com/pinned-octocat.svg" color="#4078c0">
-      <link rel="icon" type="image/x-icon" href="https://assets-cdn.github.com/favicon.ico">
-
-    <meta name="html-safe-nonce" content="deea0f406df2fb95709865c5ee80a255d8c47fa9">
-    <meta content="736eea9d74cf34fe850d2180e8a5f0a1cc7bc0be" name="form-nonce" />
-
-    <meta http-equiv="x-pjax-version" content="f302977937abe3fe1c9a4d4bed913565">
-    
-
-      
-  <meta name="description" content="nativejson-benchmark - C/C++ JSON parser/generator benchmark">
-  <meta name="go-import" content="github.com/miloyip/nativejson-benchmark git https://github.com/miloyip/nativejson-benchmark.git">
-
-  <meta content="1195774" name="octolytics-dimension-user_id" /><meta content="miloyip" name="octolytics-dimension-user_login" /><meta content="22976798" name="octolytics-dimension-repository_id" /><meta content="miloyip/nativejson-benchmark" name="octolytics-dimension-repository_nwo" /><meta content="true" name="octolytics-dimension-repository_public" /><meta content="false" name="octolytics-dimension-repository_is_fork" /><meta content="22976798" name="octolytics-dimension-repository_network_root_id" /><meta content="miloyip/nativejson-benchmark" name="octolytics-dimension-repository_network_root_nwo" />
-  <link href="https://github.com/miloyip/nativejson-benchmark/commits/master.atom" rel="alternate" title="Recent Commits to nativejson-benchmark:master" type="application/atom+xml">
-
-
-      <link rel="canonical" href="https://github.com/miloyip/nativejson-benchmark/blob/master/sample/conformance_Nlohmann%20(C%2B%2B11).md" data-pjax-transient>
-  </head>
-
-
-  <body class="logged-out  env-production  vis-public page-blob">
-    <div id="js-pjax-loader-bar" class="pjax-loader-bar"><div class="progress"></div></div>
-    <a href="#start-of-content" tabindex="1" class="accessibility-aid js-skip-to-content">Skip to content</a>
-
-    
-    
-    
-
-
-
-          <header class="site-header js-details-container" role="banner">
-  <div class="container-responsive">
-    <a class="header-logo-invertocat" href="https://github.com/" aria-label="Homepage" data-ga-click="(Logged out) Header, go to homepage, icon:logo-wordmark">
-      <svg aria-hidden="true" class="octicon octicon-mark-github" height="32" version="1.1" viewBox="0 0 16 16" width="32"><path d="M8 0C3.58 0 0 3.58 0 8c0 3.54 2.29 6.53 5.47 7.59.4.07.55-.17.55-.38 0-.19-.01-.82-.01-1.49-2.01.37-2.53-.49-2.69-.94-.09-.23-.48-.94-.82-1.13-.28-.15-.68-.52-.01-.53.63-.01 1.08.58 1.23.82.72 1.21 1.87.87 2.33.66.07-.52.28-.87.51-1.07-1.78-.2-3.64-.89-3.64-3.95 0-.87.31-1.59.82-2.15-.08-.2-.36-1.02.08-2.12 0 0 .67-.21 2.2.82.64-.18 1.32-.27 2-.27.68 0 1.36.09 2 .27 1.53-1.04 2.2-.82 2.2-.82.44 1.1.16 1.92.08 2.12.51.56.82 1.27.82 2.15 0 3.07-1.87 3.75-3.65 3.95.29.25.54.73.54 1.48 0 1.07-.01 1.93-.01 2.2 0 .21.15.46.55.38A8.013 8.013 0 0 0 16 8c0-4.42-3.58-8-8-8z"></path></svg>
-    </a>
-
-    <button class="btn-link float-right site-header-toggle js-details-target" type="button" aria-label="Toggle navigation">
-      <svg aria-hidden="true" class="octicon octicon-three-bars" height="24" version="1.1" viewBox="0 0 12 16" width="18"><path d="M11.41 9H.59C0 9 0 8.59 0 8c0-.59 0-1 .59-1H11.4c.59 0 .59.41.59 1 0 .59 0 1-.59 1h.01zm0-4H.59C0 5 0 4.59 0 4c0-.59 0-1 .59-1H11.4c.59 0 .59.41.59 1 0 .59 0 1-.59 1h.01zM.59 11H11.4c.59 0 .59.41.59 1 0 .59 0 1-.59 1H.59C0 13 0 12.59 0 12c0-.59 0-1 .59-1z"></path></svg>
-    </button>
-
-    <div class="site-header-menu">
-      <nav class="site-header-nav site-header-nav-main">
-        <a href="/personal" class="js-selected-navigation-item nav-item nav-item-personal" data-ga-click="Header, click, Nav menu - item:personal" data-selected-links="/personal /personal">
-          Personal
-</a>        <a href="/open-source" class="js-selected-navigation-item nav-item nav-item-opensource" data-ga-click="Header, click, Nav menu - item:opensource" data-selected-links="/open-source /open-source">
-          Open source
-</a>        <a href="/business" class="js-selected-navigation-item nav-item nav-item-business" data-ga-click="Header, click, Nav menu - item:business" data-selected-links="/business /business/partners /business/features /business/customers /business">
-          Business
-</a>        <a href="/explore" class="js-selected-navigation-item nav-item nav-item-explore" data-ga-click="Header, click, Nav menu - item:explore" data-selected-links="/explore /trending /trending/developers /integrations /integrations/feature/code /integrations/feature/collaborate /integrations/feature/ship /explore">
-          Explore
-</a>      </nav>
-
-      <div class="site-header-actions">
-            <a class="btn btn-primary site-header-actions-btn" href="/join?source=header-repo" data-ga-click="(Logged out) Header, clicked Sign up, text:sign-up">Sign up</a>
-          <a class="btn site-header-actions-btn mr-2" href="/login?return_to=%2Fmiloyip%2Fnativejson-benchmark%2Fblob%2Fmaster%2Fsample%2Fconformance_Nlohmann%2520%28C%252B%252B11%29.md" data-ga-click="(Logged out) Header, clicked Sign in, text:sign-in">Sign in</a>
-      </div>
-
-        <nav class="site-header-nav site-header-nav-secondary">
-          <a class="nav-item" href="/pricing">Pricing</a>
-          <a class="nav-item" href="/blog">Blog</a>
-          <a class="nav-item" href="https://help.github.com">Support</a>
-          <a class="nav-item header-search-link" href="https://github.com/search">Search GitHub</a>
-              <div class="header-search scoped-search site-scoped-search js-site-search" role="search">
-  <!-- </textarea> --><!-- '"` --><form accept-charset="UTF-8" action="/miloyip/nativejson-benchmark/search" class="js-site-search-form" data-scoped-search-url="/miloyip/nativejson-benchmark/search" data-unscoped-search-url="/search" method="get"><div style="margin:0;padding:0;display:inline"><input name="utf8" type="hidden" value="&#x2713;" /></div>
-    <label class="form-control header-search-wrapper js-chromeless-input-container">
-      <div class="header-search-scope">This repository</div>
-      <input type="text"
-        class="form-control header-search-input js-site-search-focus js-site-search-field is-clearable"
-        data-hotkey="s"
-        name="q"
-        placeholder="Search"
-        aria-label="Search this repository"
-        data-unscoped-placeholder="Search GitHub"
-        data-scoped-placeholder="Search"
-        autocapitalize="off">
-    </label>
-</form></div>
-
-        </nav>
-    </div>
-  </div>
-</header>
-
-
-
-    <div id="start-of-content" class="accessibility-aid"></div>
-
-      <div id="js-flash-container">
-</div>
-
-
-    <div role="main">
-        <div itemscope itemtype="http://schema.org/SoftwareSourceCode">
-    <div id="js-repo-pjax-container" data-pjax-container>
-      
-<div class="pagehead repohead instapaper_ignore readability-menu experiment-repo-nav">
-  <div class="container repohead-details-container">
-
-    
-
-<ul class="pagehead-actions">
-
-  <li>
-      <a href="/login?return_to=%2Fmiloyip%2Fnativejson-benchmark"
-    class="btn btn-sm btn-with-count tooltipped tooltipped-n"
-    aria-label="You must be signed in to watch a repository" rel="nofollow">
-    <svg aria-hidden="true" class="octicon octicon-eye" height="16" version="1.1" viewBox="0 0 16 16" width="16"><path d="M8.06 2C3 2 0 8 0 8s3 6 8.06 6C13 14 16 8 16 8s-3-6-7.94-6zM8 12c-2.2 0-4-1.78-4-4 0-2.2 1.8-4 4-4 2.22 0 4 1.8 4 4 0 2.22-1.78 4-4 4zm2-4c0 1.11-.89 2-2 2-1.11 0-2-.89-2-2 0-1.11.89-2 2-2 1.11 0 2 .89 2 2z"></path></svg>
-    Watch
-  </a>
-  <a class="social-count" href="/miloyip/nativejson-benchmark/watchers"
-     aria-label="40 users are watching this repository">
-    40
-  </a>
-
-  </li>
-
-  <li>
-      <a href="/login?return_to=%2Fmiloyip%2Fnativejson-benchmark"
-    class="btn btn-sm btn-with-count tooltipped tooltipped-n"
-    aria-label="You must be signed in to star a repository" rel="nofollow">
-    <svg aria-hidden="true" class="octicon octicon-star" height="16" version="1.1" viewBox="0 0 14 16" width="14"><path d="M14 6l-4.9-.64L7 1 4.9 5.36 0 6l3.6 3.26L2.67 14 7 11.67 11.33 14l-.93-4.74z"></path></svg>
-    Star
-  </a>
-
-    <a class="social-count js-social-count" href="/miloyip/nativejson-benchmark/stargazers"
-      aria-label="352 users starred this repository">
-      352
-    </a>
-
-  </li>
-
-  <li>
-      <a href="/login?return_to=%2Fmiloyip%2Fnativejson-benchmark"
-        class="btn btn-sm btn-with-count tooltipped tooltipped-n"
-        aria-label="You must be signed in to fork a repository" rel="nofollow">
-        <svg aria-hidden="true" class="octicon octicon-repo-forked" height="16" version="1.1" viewBox="0 0 10 16" width="10"><path d="M8 1a1.993 1.993 0 0 0-1 3.72V6L5 8 3 6V4.72A1.993 1.993 0 0 0 2 1a1.993 1.993 0 0 0-1 3.72V6.5l3 3v1.78A1.993 1.993 0 0 0 5 15a1.993 1.993 0 0 0 1-3.72V9.5l3-3V4.72A1.993 1.993 0 0 0 8 1zM2 4.2C1.34 4.2.8 3.65.8 3c0-.65.55-1.2 1.2-1.2.65 0 1.2.55 1.2 1.2 0 .65-.55 1.2-1.2 1.2zm3 10c-.66 0-1.2-.55-1.2-1.2 0-.65.55-1.2 1.2-1.2.65 0 1.2.55 1.2 1.2 0 .65-.55 1.2-1.2 1.2zm3-10c-.66 0-1.2-.55-1.2-1.2 0-.65.55-1.2 1.2-1.2.65 0 1.2.55 1.2 1.2 0 .65-.55 1.2-1.2 1.2z"></path></svg>
-        Fork
-      </a>
-
-    <a href="/miloyip/nativejson-benchmark/network" class="social-count"
-       aria-label="59 users are forked this repository">
-      59
-    </a>
-  </li>
-</ul>
-
-    <h1 class="public ">
-  <svg aria-hidden="true" class="octicon octicon-repo" height="16" version="1.1" viewBox="0 0 12 16" width="12"><path d="M4 9H3V8h1v1zm0-3H3v1h1V6zm0-2H3v1h1V4zm0-2H3v1h1V2zm8-1v12c0 .55-.45 1-1 1H6v2l-1.5-1.5L3 16v-2H1c-.55 0-1-.45-1-1V1c0-.55.45-1 1-1h10c.55 0 1 .45 1 1zm-1 10H1v2h2v-1h3v1h5v-2zm0-10H2v9h9V1z"></path></svg>
-  <span class="author" itemprop="author"><a href="/miloyip" class="url fn" rel="author">miloyip</a></span><!--
---><span class="path-divider">/</span><!--
---><strong itemprop="name"><a href="/miloyip/nativejson-benchmark" data-pjax="#js-repo-pjax-container">nativejson-benchmark</a></strong>
-
-</h1>
-
-  </div>
-  <div class="container">
-    
-<nav class="reponav js-repo-nav js-sidenav-container-pjax"
-     itemscope
-     itemtype="http://schema.org/BreadcrumbList"
-     role="navigation"
-     data-pjax="#js-repo-pjax-container">
-
-  <span itemscope itemtype="http://schema.org/ListItem" itemprop="itemListElement">
-    <a href="/miloyip/nativejson-benchmark" aria-selected="true" class="js-selected-navigation-item selected reponav-item" data-hotkey="g c" data-selected-links="repo_source repo_downloads repo_commits repo_releases repo_tags repo_branches /miloyip/nativejson-benchmark" itemprop="url">
-      <svg aria-hidden="true" class="octicon octicon-code" height="16" version="1.1" viewBox="0 0 14 16" width="14"><path d="M9.5 3L8 4.5 11.5 8 8 11.5 9.5 13 14 8 9.5 3zm-5 0L0 8l4.5 5L6 11.5 2.5 8 6 4.5 4.5 3z"></path></svg>
-      <span itemprop="name">Code</span>
-      <meta itemprop="position" content="1">
-</a>  </span>
-
-    <span itemscope itemtype="http://schema.org/ListItem" itemprop="itemListElement">
-      <a href="/miloyip/nativejson-benchmark/issues" class="js-selected-navigation-item reponav-item" data-hotkey="g i" data-selected-links="repo_issues repo_labels repo_milestones /miloyip/nativejson-benchmark/issues" itemprop="url">
-        <svg aria-hidden="true" class="octicon octicon-issue-opened" height="16" version="1.1" viewBox="0 0 14 16" width="14"><path d="M7 2.3c3.14 0 5.7 2.56 5.7 5.7s-2.56 5.7-5.7 5.7A5.71 5.71 0 0 1 1.3 8c0-3.14 2.56-5.7 5.7-5.7zM7 1C3.14 1 0 4.14 0 8s3.14 7 7 7 7-3.14 7-7-3.14-7-7-7zm1 3H6v5h2V4zm0 6H6v2h2v-2z"></path></svg>
-        <span itemprop="name">Issues</span>
-        <span class="counter">8</span>
-        <meta itemprop="position" content="2">
-</a>    </span>
-
-  <span itemscope itemtype="http://schema.org/ListItem" itemprop="itemListElement">
-    <a href="/miloyip/nativejson-benchmark/pulls" class="js-selected-navigation-item reponav-item" data-hotkey="g p" data-selected-links="repo_pulls /miloyip/nativejson-benchmark/pulls" itemprop="url">
-      <svg aria-hidden="true" class="octicon octicon-git-pull-request" height="16" version="1.1" viewBox="0 0 12 16" width="12"><path d="M11 11.28V5c-.03-.78-.34-1.47-.94-2.06C9.46 2.35 8.78 2.03 8 2H7V0L4 3l3 3V4h1c.27.02.48.11.69.31.21.2.3.42.31.69v6.28A1.993 1.993 0 0 0 10 15a1.993 1.993 0 0 0 1-3.72zm-1 2.92c-.66 0-1.2-.55-1.2-1.2 0-.65.55-1.2 1.2-1.2.65 0 1.2.55 1.2 1.2 0 .65-.55 1.2-1.2 1.2zM4 3c0-1.11-.89-2-2-2a1.993 1.993 0 0 0-1 3.72v6.56A1.993 1.993 0 0 0 2 15a1.993 1.993 0 0 0 1-3.72V4.72c.59-.34 1-.98 1-1.72zm-.8 10c0 .66-.55 1.2-1.2 1.2-.65 0-1.2-.55-1.2-1.2 0-.65.55-1.2 1.2-1.2.65 0 1.2.55 1.2 1.2zM2 4.2C1.34 4.2.8 3.65.8 3c0-.65.55-1.2 1.2-1.2.65 0 1.2.55 1.2 1.2 0 .65-.55 1.2-1.2 1.2z"></path></svg>
-      <span itemprop="name">Pull requests</span>
-      <span class="counter">1</span>
-      <meta itemprop="position" content="3">
-</a>  </span>
-
-
-
-
-  <a href="/miloyip/nativejson-benchmark/pulse" class="js-selected-navigation-item reponav-item" data-selected-links="pulse /miloyip/nativejson-benchmark/pulse">
-    <svg aria-hidden="true" class="octicon octicon-pulse" height="16" version="1.1" viewBox="0 0 14 16" width="14"><path d="M11.5 8L8.8 5.4 6.6 8.5 5.5 1.6 2.38 8H0v2h3.6l.9-1.8.9 5.4L9 8.5l1.6 1.5H14V8z"></path></svg>
-    Pulse
-</a>
-  <a href="/miloyip/nativejson-benchmark/graphs" class="js-selected-navigation-item reponav-item" data-selected-links="repo_graphs repo_contributors /miloyip/nativejson-benchmark/graphs">
-    <svg aria-hidden="true" class="octicon octicon-graph" height="16" version="1.1" viewBox="0 0 16 16" width="16"><path d="M16 14v1H0V0h1v14h15zM5 13H3V8h2v5zm4 0H7V3h2v10zm4 0h-2V6h2v7z"></path></svg>
-    Graphs
-</a>
-
-</nav>
-
-  </div>
-</div>
-
-<div class="container new-discussion-timeline experiment-repo-nav">
-  <div class="repository-content">
-
-    
-
-<a href="/miloyip/nativejson-benchmark/blob/95f27ebcf9a96c7ca4cee26467ed5420140090fb/sample/conformance_Nlohmann%20(C%2B%2B11).md" class="d-none js-permalink-shortcut" data-hotkey="y">Permalink</a>
-
-<!-- blob contrib key: blob_contributors:v21:0bf9e3593dedd91db6c9dc69e13b7f95 -->
-
-<div class="file-navigation js-zeroclipboard-container">
-  
-<div class="select-menu branch-select-menu js-menu-container js-select-menu float-left">
-  <button class="btn btn-sm select-menu-button js-menu-target css-truncate" data-hotkey="w"
-    
-    type="button" aria-label="Switch branches or tags" tabindex="0" aria-haspopup="true">
-    <i>Branch:</i>
-    <span class="js-select-button css-truncate-target">master</span>
-  </button>
-
-  <div class="select-menu-modal-holder js-menu-content js-navigation-container" data-pjax aria-hidden="true">
-
-    <div class="select-menu-modal">
-      <div class="select-menu-header">
-        <svg aria-label="Close" class="octicon octicon-x js-menu-close" height="16" role="img" version="1.1" viewBox="0 0 12 16" width="12"><path d="M7.48 8l3.75 3.75-1.48 1.48L6 9.48l-3.75 3.75-1.48-1.48L4.52 8 .77 4.25l1.48-1.48L6 6.52l3.75-3.75 1.48 1.48z"></path></svg>
-        <span class="select-menu-title">Switch branches/tags</span>
-      </div>
-
-      <div class="select-menu-filters">
-        <div class="select-menu-text-filter">
-          <input type="text" aria-label="Filter branches/tags" id="context-commitish-filter-field" class="form-control js-filterable-field js-navigation-enable" placeholder="Filter branches/tags">
-        </div>
-        <div class="select-menu-tabs">
-          <ul>
-            <li class="select-menu-tab">
-              <a href="#" data-tab-filter="branches" data-filter-placeholder="Filter branches/tags" class="js-select-menu-tab" role="tab">Branches</a>
-            </li>
-            <li class="select-menu-tab">
-              <a href="#" data-tab-filter="tags" data-filter-placeholder="Find a tag…" class="js-select-menu-tab" role="tab">Tags</a>
-            </li>
-          </ul>
-        </div>
-      </div>
-
-      <div class="select-menu-list select-menu-tab-bucket js-select-menu-tab-bucket" data-tab-filter="branches" role="menu">
-
-        <div data-filterable-for="context-commitish-filter-field" data-filterable-type="substring">
-
-
-            <a class="select-menu-item js-navigation-item js-navigation-open "
-               href="/miloyip/nativejson-benchmark/blob/Stixjson/sample/conformance_Nlohmann%20(C++11).md"
-               data-name="Stixjson"
-               data-skip-pjax="true"
-               rel="nofollow">
-              <svg aria-hidden="true" class="octicon octicon-check select-menu-item-icon" height="16" version="1.1" viewBox="0 0 12 16" width="12"><path d="M12 5l-8 8-4-4 1.5-1.5L4 10l6.5-6.5z"></path></svg>
-              <span class="select-menu-item-text css-truncate-target js-select-menu-filter-text">
-                Stixjson
-              </span>
-            </a>
-            <a class="select-menu-item js-navigation-item js-navigation-open "
-               href="/miloyip/nativejson-benchmark/blob/ccan/sample/conformance_Nlohmann%20(C++11).md"
-               data-name="ccan"
-               data-skip-pjax="true"
-               rel="nofollow">
-              <svg aria-hidden="true" class="octicon octicon-check select-menu-item-icon" height="16" version="1.1" viewBox="0 0 12 16" width="12"><path d="M12 5l-8 8-4-4 1.5-1.5L4 10l6.5-6.5z"></path></svg>
-              <span class="select-menu-item-text css-truncate-target js-select-menu-filter-text">
-                ccan
-              </span>
-            </a>
-            <a class="select-menu-item js-navigation-item js-navigation-open "
-               href="/miloyip/nativejson-benchmark/blob/jbson/sample/conformance_Nlohmann%20(C++11).md"
-               data-name="jbson"
-               data-skip-pjax="true"
-               rel="nofollow">
-              <svg aria-hidden="true" class="octicon octicon-check select-menu-item-icon" height="16" version="1.1" viewBox="0 0 12 16" width="12"><path d="M12 5l-8 8-4-4 1.5-1.5L4 10l6.5-6.5z"></path></svg>
-              <span class="select-menu-item-text css-truncate-target js-select-menu-filter-text">
-                jbson
-              </span>
-            </a>
-            <a class="select-menu-item js-navigation-item js-navigation-open "
-               href="/miloyip/nativejson-benchmark/blob/jute/sample/conformance_Nlohmann%20(C++11).md"
-               data-name="jute"
-               data-skip-pjax="true"
-               rel="nofollow">
-              <svg aria-hidden="true" class="octicon octicon-check select-menu-item-icon" height="16" version="1.1" viewBox="0 0 12 16" width="12"><path d="M12 5l-8 8-4-4 1.5-1.5L4 10l6.5-6.5z"></path></svg>
-              <span class="select-menu-item-text css-truncate-target js-select-menu-filter-text">
-                jute
-              </span>
-            </a>
-            <a class="select-menu-item js-navigation-item js-navigation-open "
-               href="/miloyip/nativejson-benchmark/blob/lastjson/sample/conformance_Nlohmann%20(C++11).md"
-               data-name="lastjson"
-               data-skip-pjax="true"
-               rel="nofollow">
-              <svg aria-hidden="true" class="octicon octicon-check select-menu-item-icon" height="16" version="1.1" viewBox="0 0 12 16" width="12"><path d="M12 5l-8 8-4-4 1.5-1.5L4 10l6.5-6.5z"></path></svg>
-              <span class="select-menu-item-text css-truncate-target js-select-menu-filter-text">
-                lastjson
-              </span>
-            </a>
-            <a class="select-menu-item js-navigation-item js-navigation-open "
-               href="/miloyip/nativejson-benchmark/blob/libjson/sample/conformance_Nlohmann%20(C++11).md"
-               data-name="libjson"
-               data-skip-pjax="true"
-               rel="nofollow">
-              <svg aria-hidden="true" class="octicon octicon-check select-menu-item-icon" height="16" version="1.1" viewBox="0 0 12 16" width="12"><path d="M12 5l-8 8-4-4 1.5-1.5L4 10l6.5-6.5z"></path></svg>
-              <span class="select-menu-item-text css-truncate-target js-select-menu-filter-text">
-                libjson
-              </span>
-            </a>
-            <a class="select-menu-item js-navigation-item js-navigation-open selected"
-               href="/miloyip/nativejson-benchmark/blob/master/sample/conformance_Nlohmann%20(C++11).md"
-               data-name="master"
-               data-skip-pjax="true"
-               rel="nofollow">
-              <svg aria-hidden="true" class="octicon octicon-check select-menu-item-icon" height="16" version="1.1" viewBox="0 0 12 16" width="12"><path d="M12 5l-8 8-4-4 1.5-1.5L4 10l6.5-6.5z"></path></svg>
-              <span class="select-menu-item-text css-truncate-target js-select-menu-filter-text">
-                master
-              </span>
-            </a>
-            <a class="select-menu-item js-navigation-item js-navigation-open "
-               href="/miloyip/nativejson-benchmark/blob/qt/sample/conformance_Nlohmann%20(C++11).md"
-               data-name="qt"
-               data-skip-pjax="true"
-               rel="nofollow">
-              <svg aria-hidden="true" class="octicon octicon-check select-menu-item-icon" height="16" version="1.1" viewBox="0 0 12 16" width="12"><path d="M12 5l-8 8-4-4 1.5-1.5L4 10l6.5-6.5z"></path></svg>
-              <span class="select-menu-item-text css-truncate-target js-select-menu-filter-text">
-                qt
-              </span>
-            </a>
-            <a class="select-menu-item js-navigation-item js-navigation-open "
-               href="/miloyip/nativejson-benchmark/blob/tunnuz/sample/conformance_Nlohmann%20(C++11).md"
-               data-name="tunnuz"
-               data-skip-pjax="true"
-               rel="nofollow">
-              <svg aria-hidden="true" class="octicon octicon-check select-menu-item-icon" height="16" version="1.1" viewBox="0 0 12 16" width="12"><path d="M12 5l-8 8-4-4 1.5-1.5L4 10l6.5-6.5z"></path></svg>
-              <span class="select-menu-item-text css-truncate-target js-select-menu-filter-text">
-                tunnuz
-              </span>
-            </a>
-            <a class="select-menu-item js-navigation-item js-navigation-open "
-               href="/miloyip/nativejson-benchmark/blob/ujson/sample/conformance_Nlohmann%20(C++11).md"
-               data-name="ujson"
-               data-skip-pjax="true"
-               rel="nofollow">
-              <svg aria-hidden="true" class="octicon octicon-check select-menu-item-icon" height="16" version="1.1" viewBox="0 0 12 16" width="12"><path d="M12 5l-8 8-4-4 1.5-1.5L4 10l6.5-6.5z"></path></svg>
-              <span class="select-menu-item-text css-truncate-target js-select-menu-filter-text">
-                ujson
-              </span>
-            </a>
-        </div>
-
-          <div class="select-menu-no-results">Nothing to show</div>
-      </div>
-
-      <div class="select-menu-list select-menu-tab-bucket js-select-menu-tab-bucket" data-tab-filter="tags">
-        <div data-filterable-for="context-commitish-filter-field" data-filterable-type="substring">
-
-
-            <a class="select-menu-item js-navigation-item js-navigation-open "
-              href="/miloyip/nativejson-benchmark/tree/v1.0.0/sample/conformance_Nlohmann%20(C%2B%2B11).md"
-              data-name="v1.0.0"
-              data-skip-pjax="true"
-              rel="nofollow">
-              <svg aria-hidden="true" class="octicon octicon-check select-menu-item-icon" height="16" version="1.1" viewBox="0 0 12 16" width="12"><path d="M12 5l-8 8-4-4 1.5-1.5L4 10l6.5-6.5z"></path></svg>
-              <span class="select-menu-item-text css-truncate-target" title="v1.0.0">
-                v1.0.0
-              </span>
-            </a>
-        </div>
-
-        <div class="select-menu-no-results">Nothing to show</div>
-      </div>
-
-    </div>
-  </div>
-</div>
-
-  <div class="btn-group float-right">
-    <a href="/miloyip/nativejson-benchmark/find/master"
-          class="js-pjax-capture-input btn btn-sm"
-          data-pjax
-          data-hotkey="t">
-      Find file
-    </a>
-    <button aria-label="Copy file path to clipboard" class="js-zeroclipboard btn btn-sm zeroclipboard-button tooltipped tooltipped-s" data-copied-hint="Copied!" type="button">Copy path</button>
-  </div>
-  <div class="breadcrumb js-zeroclipboard-target">
-    <span class="repo-root js-repo-root"><span class="js-path-segment"><a href="/miloyip/nativejson-benchmark"><span>nativejson-benchmark</span></a></span></span><span class="separator">/</span><span class="js-path-segment"><a href="/miloyip/nativejson-benchmark/tree/master/sample"><span>sample</span></a></span><span class="separator">/</span><strong class="final-path">conformance_Nlohmann (C++11).md</strong>
-  </div>
-</div>
-
-
-  <div class="commit-tease">
-      <span class="float-right">
-        <a class="commit-tease-sha" href="/miloyip/nativejson-benchmark/commit/a4a9f10f41c515d6abb0f019ab9f5d021ed4bb9e" data-pjax>
-          a4a9f10
-        </a>
-        <relative-time datetime="2016-09-09T03:15:21Z">Sep 9, 2016</relative-time>
-      </span>
-      <div>
-        <img alt="@miloyip" class="avatar" height="20" src="https://avatars3.githubusercontent.com/u/1195774?v=3&amp;s=40" width="20" />
-        <a href="/miloyip" class="user-mention" rel="author">miloyip</a>
-          <a href="/miloyip/nativejson-benchmark/commit/a4a9f10f41c515d6abb0f019ab9f5d021ed4bb9e" class="message" data-pjax="true" title="Update sample result for 41 libraries
-
-Fixed #43">Update sample result for 41 libraries</a>
-      </div>
-
-    <div class="commit-tease-contributors">
-      <button type="button" class="btn-link muted-link contributors-toggle" data-facebox="#blob_contributors_box">
-        <strong>1</strong>
-         contributor
-      </button>
-      
-    </div>
-
-    <div id="blob_contributors_box" style="display:none">
-      <h2 class="facebox-header" data-facebox-id="facebox-header">Users who have contributed to this file</h2>
-      <ul class="facebox-user-list" data-facebox-id="facebox-description">
-          <li class="facebox-user-list-item">
-            <img alt="@miloyip" height="24" src="https://avatars1.githubusercontent.com/u/1195774?v=3&amp;s=48" width="24" />
-            <a href="/miloyip">miloyip</a>
-          </li>
-      </ul>
-    </div>
-  </div>
-
-<div class="file">
-  <div class="file-header">
-  <div class="file-actions">
-
-    <div class="btn-group">
-      <a href="/miloyip/nativejson-benchmark/raw/master/sample/conformance_Nlohmann%20(C%2B%2B11).md" class="btn btn-sm " id="raw-url">Raw</a>
-        <a href="/miloyip/nativejson-benchmark/blame/master/sample/conformance_Nlohmann%20(C%2B%2B11).md" class="btn btn-sm js-update-url-with-hash">Blame</a>
-      <a href="/miloyip/nativejson-benchmark/commits/master/sample/conformance_Nlohmann%20(C%2B%2B11).md" class="btn btn-sm " rel="nofollow">History</a>
-    </div>
-
-
-        <button type="button" class="btn-octicon disabled tooltipped tooltipped-nw"
-          aria-label="You must be signed in to make or propose changes">
-          <svg aria-hidden="true" class="octicon octicon-pencil" height="16" version="1.1" viewBox="0 0 14 16" width="14"><path d="M0 12v3h3l8-8-3-3-8 8zm3 2H1v-2h1v1h1v1zm10.3-9.3L12 6 9 3l1.3-1.3a.996.996 0 0 1 1.41 0l1.59 1.59c.39.39.39 1.02 0 1.41z"></path></svg>
-        </button>
-        <button type="button" class="btn-octicon btn-octicon-danger disabled tooltipped tooltipped-nw"
-          aria-label="You must be signed in to make or propose changes">
-          <svg aria-hidden="true" class="octicon octicon-trashcan" height="16" version="1.1" viewBox="0 0 12 16" width="12"><path d="M11 2H9c0-.55-.45-1-1-1H5c-.55 0-1 .45-1 1H2c-.55 0-1 .45-1 1v1c0 .55.45 1 1 1v9c0 .55.45 1 1 1h7c.55 0 1-.45 1-1V5c.55 0 1-.45 1-1V3c0-.55-.45-1-1-1zm-1 12H3V5h1v8h1V5h1v8h1V5h1v8h1V5h1v9zm1-10H2V3h9v1z"></path></svg>
-        </button>
-  </div>
-
-  <div class="file-info">
-      59 lines (37 sloc)
-      <span class="file-info-divider"></span>
-    545 Bytes
-  </div>
-</div>
-
-  
-  <div id="readme" class="readme blob instapaper_body">
-    <article class="markdown-body entry-content" itemprop="text"><h1><a id="user-content-conformance-of-nlohmann-c11" class="anchor" href="#conformance-of-nlohmann-c11" aria-hidden="true"><svg aria-hidden="true" class="octicon octicon-link" height="16" version="1.1" viewBox="0 0 16 16" width="16"><path d="M4 9h1v1H4c-1.5 0-3-1.69-3-3.5S2.55 3 4 3h4c1.45 0 3 1.69 3 3.5 0 1.41-.91 2.72-2 3.25V8.59c.58-.45 1-1.27 1-2.09C10 5.22 8.98 4 8 4H4c-.98 0-2 1.22-2 2.5S3 9 4 9zm9-3h-1v1h1c1 0 2 1.22 2 2.5S13.98 12 13 12H9c-.98 0-2-1.22-2-2.5 0-.83.42-1.64 1-2.09V6.25c-1.09.53-2 1.84-2 3.25C6 11.31 7.55 13 9 13h4c1.45 0 3-1.69 3-3.5S14.5 6 13 6z"></path></svg></a>Conformance of Nlohmann (C++11)</h1>
-
-<h2><a id="user-content-1-parse-validation" class="anchor" href="#1-parse-validation" aria-hidden="true"><svg aria-hidden="true" class="octicon octicon-link" height="16" version="1.1" viewBox="0 0 16 16" width="16"><path d="M4 9h1v1H4c-1.5 0-3-1.69-3-3.5S2.55 3 4 3h4c1.45 0 3 1.69 3 3.5 0 1.41-.91 2.72-2 3.25V8.59c.58-.45 1-1.27 1-2.09C10 5.22 8.98 4 8 4H4c-.98 0-2 1.22-2 2.5S3 9 4 9zm9-3h-1v1h1c1 0 2 1.22 2 2.5S13.98 12 13 12H9c-.98 0-2-1.22-2-2.5 0-.83.42-1.64 1-2.09V6.25c-1.09.53-2 1.84-2 3.25C6 11.31 7.55 13 9 13h4c1.45 0 3-1.69 3-3.5S14.5 6 13 6z"></path></svg></a>1. Parse Validation</h2>
-
-<p>Summary: 34 of 34 are correct.</p>
-
-<h2><a id="user-content-2-parse-double" class="anchor" href="#2-parse-double" aria-hidden="true"><svg aria-hidden="true" class="octicon octicon-link" height="16" version="1.1" viewBox="0 0 16 16" width="16"><path d="M4 9h1v1H4c-1.5 0-3-1.69-3-3.5S2.55 3 4 3h4c1.45 0 3 1.69 3 3.5 0 1.41-.91 2.72-2 3.25V8.59c.58-.45 1-1.27 1-2.09C10 5.22 8.98 4 8 4H4c-.98 0-2 1.22-2 2.5S3 9 4 9zm9-3h-1v1h1c1 0 2 1.22 2 2.5S13.98 12 13 12H9c-.98 0-2-1.22-2-2.5 0-.83.42-1.64 1-2.09V6.25c-1.09.53-2 1.84-2 3.25C6 11.31 7.55 13 9 13h4c1.45 0 3-1.69 3-3.5S14.5 6 13 6z"></path></svg></a>2. Parse Double</h2>
-
-<p>Summary: 66 of 66 are correct.</p>
-
-<h2><a id="user-content-3-parse-string" class="anchor" href="#3-parse-string" aria-hidden="true"><svg aria-hidden="true" class="octicon octicon-link" height="16" version="1.1" viewBox="0 0 16 16" width="16"><path d="M4 9h1v1H4c-1.5 0-3-1.69-3-3.5S2.55 3 4 3h4c1.45 0 3 1.69 3 3.5 0 1.41-.91 2.72-2 3.25V8.59c.58-.45 1-1.27 1-2.09C10 5.22 8.98 4 8 4H4c-.98 0-2 1.22-2 2.5S3 9 4 9zm9-3h-1v1h1c1 0 2 1.22 2 2.5S13.98 12 13 12H9c-.98 0-2-1.22-2-2.5 0-.83.42-1.64 1-2.09V6.25c-1.09.53-2 1.84-2 3.25C6 11.31 7.55 13 9 13h4c1.45 0 3-1.69 3-3.5S14.5 6 13 6z"></path></svg></a>3. Parse String</h2>
-
-<p>Summary: 9 of 9 are correct.</p>
-
-<h2><a id="user-content-4-roundtrip" class="anchor" href="#4-roundtrip" aria-hidden="true"><svg aria-hidden="true" class="octicon octicon-link" height="16" version="1.1" viewBox="0 0 16 16" width="16"><path d="M4 9h1v1H4c-1.5 0-3-1.69-3-3.5S2.55 3 4 3h4c1.45 0 3 1.69 3 3.5 0 1.41-.91 2.72-2 3.25V8.59c.58-.45 1-1.27 1-2.09C10 5.22 8.98 4 8 4H4c-.98 0-2 1.22-2 2.5S3 9 4 9zm9-3h-1v1h1c1 0 2 1.22 2 2.5S13.98 12 13 12H9c-.98 0-2-1.22-2-2.5 0-.83.42-1.64 1-2.09V6.25c-1.09.53-2 1.84-2 3.25C6 11.31 7.55 13 9 13h4c1.45 0 3-1.69 3-3.5S14.5 6 13 6z"></path></svg></a>4. Roundtrip</h2>
-
-<ul>
-<li>Fail:</li>
-</ul>
-
-<div class="highlight highlight-source-js"><pre>[<span class="pl-c1">5e-324</span>]</pre></div>
-
-<div class="highlight highlight-source-js"><pre>[<span class="pl-c1">4.94065645841247e-324</span>]</pre></div>
-
-<ul>
-<li>Fail:</li>
-</ul>
-
-<div class="highlight highlight-source-js"><pre>[<span class="pl-c1">2.225073858507201e-308</span>]</pre></div>
-
-<div class="highlight highlight-source-js"><pre>[<span class="pl-c1">2.2250738585072e-308</span>]</pre></div>
-
-<ul>
-<li>Fail:</li>
-</ul>
-
-<div class="highlight highlight-source-js"><pre>[<span class="pl-c1">2.2250738585072014e-308</span>]</pre></div>
-
-<div class="highlight highlight-source-js"><pre>[<span class="pl-c1">2.2250738585072e-308</span>]</pre></div>
-
-<ul>
-<li>Fail:</li>
-</ul>
-
-<div class="highlight highlight-source-js"><pre>[<span class="pl-c1">1.7976931348623157e308</span>]</pre></div>
-
-<div class="highlight highlight-source-js"><pre>[<span class="pl-c1">1.79769313486232e+308</span>]</pre></div>
-
-<p>Summary: 23 of 27 are correct.</p>
-</article>
-  </div>
-
-</div>
-
-<button type="button" data-facebox="#jump-to-line" data-facebox-class="linejump" data-hotkey="l" class="d-none">Jump to Line</button>
-<div id="jump-to-line" style="display:none">
-  <!-- </textarea> --><!-- '"` --><form accept-charset="UTF-8" action="" class="js-jump-to-line-form" method="get"><div style="margin:0;padding:0;display:inline"><input name="utf8" type="hidden" value="&#x2713;" /></div>
-    <input class="form-control linejump-input js-jump-to-line-field" type="text" placeholder="Jump to line&hellip;" aria-label="Jump to line" autofocus>
-    <button type="submit" class="btn">Go</button>
-</form></div>
-
-  </div>
-  <div class="modal-backdrop js-touch-events"></div>
-</div>
-
-
-    </div>
-  </div>
-
-    </div>
-
-        <div class="container site-footer-container">
-  <div class="site-footer" role="contentinfo">
-    <ul class="site-footer-links float-right">
-        <li><a href="https://github.com/contact" data-ga-click="Footer, go to contact, text:contact">Contact GitHub</a></li>
-      <li><a href="https://developer.github.com" data-ga-click="Footer, go to api, text:api">API</a></li>
-      <li><a href="https://training.github.com" data-ga-click="Footer, go to training, text:training">Training</a></li>
-      <li><a href="https://shop.github.com" data-ga-click="Footer, go to shop, text:shop">Shop</a></li>
-        <li><a href="https://github.com/blog" data-ga-click="Footer, go to blog, text:blog">Blog</a></li>
-        <li><a href="https://github.com/about" data-ga-click="Footer, go to about, text:about">About</a></li>
-
-    </ul>
-
-    <a href="https://github.com" aria-label="Homepage" class="site-footer-mark" title="GitHub">
-      <svg aria-hidden="true" class="octicon octicon-mark-github" height="24" version="1.1" viewBox="0 0 16 16" width="24"><path d="M8 0C3.58 0 0 3.58 0 8c0 3.54 2.29 6.53 5.47 7.59.4.07.55-.17.55-.38 0-.19-.01-.82-.01-1.49-2.01.37-2.53-.49-2.69-.94-.09-.23-.48-.94-.82-1.13-.28-.15-.68-.52-.01-.53.63-.01 1.08.58 1.23.82.72 1.21 1.87.87 2.33.66.07-.52.28-.87.51-1.07-1.78-.2-3.64-.89-3.64-3.95 0-.87.31-1.59.82-2.15-.08-.2-.36-1.02.08-2.12 0 0 .67-.21 2.2.82.64-.18 1.32-.27 2-.27.68 0 1.36.09 2 .27 1.53-1.04 2.2-.82 2.2-.82.44 1.1.16 1.92.08 2.12.51.56.82 1.27.82 2.15 0 3.07-1.87 3.75-3.65 3.95.29.25.54.73.54 1.48 0 1.07-.01 1.93-.01 2.2 0 .21.15.46.55.38A8.013 8.013 0 0 0 16 8c0-4.42-3.58-8-8-8z"></path></svg>
-</a>
-    <ul class="site-footer-links">
-      <li>&copy; 2016 <span title="0.18611s from github-fe151-cp1-prd.iad.github.net">GitHub</span>, Inc.</li>
-        <li><a href="https://github.com/site/terms" data-ga-click="Footer, go to terms, text:terms">Terms</a></li>
-        <li><a href="https://github.com/site/privacy" data-ga-click="Footer, go to privacy, text:privacy">Privacy</a></li>
-        <li><a href="https://github.com/security" data-ga-click="Footer, go to security, text:security">Security</a></li>
-        <li><a href="https://status.github.com/" data-ga-click="Footer, go to status, text:status">Status</a></li>
-        <li><a href="https://help.github.com" data-ga-click="Footer, go to help, text:help">Help</a></li>
-    </ul>
-  </div>
-</div>
-
-
-
-    
-
-    <div id="ajax-error-message" class="ajax-error-message flash flash-error">
-      <svg aria-hidden="true" class="octicon octicon-alert" height="16" version="1.1" viewBox="0 0 16 16" width="16"><path d="M8.865 1.52c-.18-.31-.51-.5-.87-.5s-.69.19-.87.5L.275 13.5c-.18.31-.18.69 0 1 .19.31.52.5.87.5h13.7c.36 0 .69-.19.86-.5.17-.31.18-.69.01-1L8.865 1.52zM8.995 13h-2v-2h2v2zm0-3h-2V6h2v4z"></path></svg>
-      <button type="button" class="flash-close js-flash-close js-ajax-error-dismiss" aria-label="Dismiss error">
-        <svg aria-hidden="true" class="octicon octicon-x" height="16" version="1.1" viewBox="0 0 12 16" width="12"><path d="M7.48 8l3.75 3.75-1.48 1.48L6 9.48l-3.75 3.75-1.48-1.48L4.52 8 .77 4.25l1.48-1.48L6 6.52l3.75-3.75 1.48 1.48z"></path></svg>
-      </button>
-      You can't perform that action at this time.
-    </div>
-
-
-      <script crossorigin="anonymous" src="https://assets-cdn.github.com/assets/compat-40e365359d1c4db1e36a55be458e60f2b7c24d58b5a00ae13398480e7ba768e0.js"></script>
-      <script crossorigin="anonymous" src="https://assets-cdn.github.com/assets/frameworks-88471af1fec40ff9418efbe2ddd15b6896af8d772f8179004c254dffc25ea490.js"></script>
-      <script async="async" crossorigin="anonymous" src="https://assets-cdn.github.com/assets/github-e18e11a943ff2eb9394c72d4ec8b76592c454915b5839ae177d422777a046e29.js"></script>
-      
-      
-      
-      
-      
-      
-    <div class="js-stale-session-flash stale-session-flash flash flash-warn flash-banner d-none">
-      <svg aria-hidden="true" class="octicon octicon-alert" height="16" version="1.1" viewBox="0 0 16 16" width="16"><path d="M8.865 1.52c-.18-.31-.51-.5-.87-.5s-.69.19-.87.5L.275 13.5c-.18.31-.18.69 0 1 .19.31.52.5.87.5h13.7c.36 0 .69-.19.86-.5.17-.31.18-.69.01-1L8.865 1.52zM8.995 13h-2v-2h2v2zm0-3h-2V6h2v4z"></path></svg>
-      <span class="signed-in-tab-flash">You signed in with another tab or window. <a href="">Reload</a> to refresh your session.</span>
-      <span class="signed-out-tab-flash">You signed out in another tab or window. <a href="">Reload</a> to refresh your session.</span>
-    </div>
-    <div class="facebox" id="facebox" style="display:none;">
-  <div class="facebox-popup">
-    <div class="facebox-content" role="dialog" aria-labelledby="facebox-header" aria-describedby="facebox-description">
-    </div>
-    <button type="button" class="facebox-close js-facebox-close" aria-label="Close modal">
-      <svg aria-hidden="true" class="octicon octicon-x" height="16" version="1.1" viewBox="0 0 12 16" width="12"><path d="M7.48 8l3.75 3.75-1.48 1.48L6 9.48l-3.75 3.75-1.48-1.48L4.52 8 .77 4.25l1.48-1.48L6 6.52l3.75-3.75 1.48 1.48z"></path></svg>
-    </button>
-  </div>
-</div>
-
-  </body>
-</html>
-

tests/reports/2016-10-02-fuzz/index.html

@@ -1,10 +0,0 @@
-<table style="font-family: 'Trebuchet MS', 'Tahoma', 'Arial', 'Helvetica'">
-<tr><td style="width: 18ex"><b>Banner:</b></td><td>fuzz</td></tr>
-<tr><td><b>Directory:</b></td><td>fuzz-testing/out</td></tr>
-<tr><td><b>Generated on:</b></td><td>Sun Oct  2 08:51:02 CEST 2016</td></tr>
-</table>
-<p>
-<img src="high_freq.png" width=1000 height=300><p>
-<img src="low_freq.png" width=1000 height=200><p>
-<img src="exec_speed.png" width=1000 height=200>
-

tests/src/fuzzer-parse_bjdata.cpp

@@ -11,15 +11,15 @@ This file implements a parser test suitable for fuzz testing. Given a byte
 array data, it performs the following steps:
 
 - j1 = from_bjdata(data)
-- vec = to_bjdata(j1)
-- j2 = from_bjdata(vec)
-- assert(j1 == j2)
-- vec2 = to_bjdata(j1, use_size = true, use_type = false)
-- j3 = from_bjdata(vec2)
-- assert(j1 == j3)
-- vec3 = to_bjdata(j1, use_size = true, use_type = true)
-- j4 = from_bjdata(vec3)
-- assert(j1 == j4)
+- vec2 = to_bjdata(j1, use_size = false, use_type = false)
+- vec3 = to_bjdata(j1, use_size = true, use_type = false)
+- vec4 = to_bjdata(j1, use_size = true, use_type = true)
+- j2 = from_bjdata(vec2)
+- j3 = from_bjdata(vec3)
+- j4 = from_bjdata(vec4)
+- assert(from_bjdata(to_bjdata(j2, use_size = false, use_type = false)) is value-stable with j2)
+- assert(from_bjdata(to_bjdata(j3, use_size = true, use_type = false)) is value-stable with j3)
+- assert(from_bjdata(to_bjdata(j4, use_size = true, use_type = true)) is value-stable with j4)
 
 Re-serializing j2/j3/j4 with the same use_size/use_type settings is checked
 for value-stability rather than byte-exact stability: from_bjdata(to_bjdata(j2))
@@ -50,8 +50,6 @@ drivers.
 */
 
 #include <cassert>
-#include <iostream>
-#include <sstream>
 #include <nlohmann/json.hpp>
 
 // the round-trip checks below are assertions; NDEBUG would compile them away

tests/src/fuzzer-parse_bon8.cpp

@@ -13,7 +13,7 @@ array data, it performs the following steps:
 - j1 = from_bon8(data)
 - vec = to_bon8(j1)
 - j2 = from_bon8(vec)
-- assert(j1 == j2)
+- assert(to_bon8(j2) == vec)
 
 It also checks that reading the data from a stream, which reads strings byte by
 byte, gives the same value or error as reading it from contiguous memory, which
@@ -24,7 +24,6 @@ drivers.
 */
 
 #include <cassert>
-#include <iostream>
 #include <sstream>
 #include <nlohmann/json.hpp>
 

tests/src/fuzzer-parse_bson.cpp

@@ -13,15 +13,13 @@ array data, it performs the following steps:
 - j1 = from_bson(data)
 - vec = to_bson(j1)
 - j2 = from_bson(vec)
-- assert(j1 == j2)
+- assert(to_bson(j2) == vec)
 
 The provided function `LLVMFuzzerTestOneInput` can be used in different fuzzer
 drivers.
 */
 
 #include <cassert>
-#include <iostream>
-#include <sstream>
 #include <nlohmann/json.hpp>
 
 // the round-trip checks below are assertions; NDEBUG would compile them away
@@ -40,11 +38,6 @@ extern "C" int LLVMFuzzerTestOneInput(const uint8_t* data, size_t size)
         std::vector<uint8_t> const vec1(data, data + size);
         json const j1 = json::from_bson(vec1);
 
-        if (j1.is_discarded())
-        {
-            return 0;
-        }
-
         try
         {
             // step 2: round trip

tests/src/fuzzer-parse_cbor.cpp

@@ -13,15 +13,13 @@ array data, it performs the following steps:
 - j1 = from_cbor(data)
 - vec = to_cbor(j1)
 - j2 = from_cbor(vec)
-- assert(j1 == j2)
+- assert(to_cbor(j2) == vec)
 
 The provided function `LLVMFuzzerTestOneInput` can be used in different fuzzer
 drivers.
 */
 
 #include <cassert>
-#include <iostream>
-#include <sstream>
 #include <nlohmann/json.hpp>
 
 // the round-trip checks below are assertions; NDEBUG would compile them away

tests/src/fuzzer-parse_json.cpp

@@ -21,8 +21,6 @@ drivers.
 */
 
 #include <cassert>
-#include <iostream>
-#include <sstream>
 #include <nlohmann/json.hpp>
 
 // the round-trip checks below are assertions; NDEBUG would compile them away

tests/src/fuzzer-parse_msgpack.cpp

@@ -13,15 +13,13 @@ array data, it performs the following steps:
 - j1 = from_msgpack(data)
 - vec = to_msgpack(j1)
 - j2 = from_msgpack(vec)
-- assert(j1 == j2)
+- assert(to_msgpack(j2) == vec)
 
 The provided function `LLVMFuzzerTestOneInput` can be used in different fuzzer
 drivers.
 */
 
 #include <cassert>
-#include <iostream>
-#include <sstream>
 #include <nlohmann/json.hpp>
 
 // the round-trip checks below are assertions; NDEBUG would compile them away

tests/src/fuzzer-parse_ubjson.cpp

@@ -11,15 +11,15 @@ This file implements a parser test suitable for fuzz testing. Given a byte
 array data, it performs the following steps:
 
 - j1 = from_ubjson(data)
-- vec = to_ubjson(j1)
-- j2 = from_ubjson(vec)
-- assert(j1 == j2)
-- vec2 = to_ubjson(j1, use_size = true, use_type = false)
-- j3 = from_ubjson(vec2)
-- assert(j1 == j3)
-- vec3 = to_ubjson(j1, use_size = true, use_type = true)
-- j4 = from_ubjson(vec3)
-- assert(j1 == j4)
+- vec2 = to_ubjson(j1, use_size = false, use_type = false)
+- vec3 = to_ubjson(j1, use_size = true, use_type = false)
+- vec4 = to_ubjson(j1, use_size = true, use_type = true)
+- j2 = from_ubjson(vec2)
+- j3 = from_ubjson(vec3)
+- j4 = from_ubjson(vec4)
+- assert(to_ubjson(j2, use_size = false, use_type = false) == vec2)
+- assert(to_ubjson(j3, use_size = true, use_type = false) == vec3)
+- assert(to_ubjson(j4, use_size = true, use_type = true) == vec4)
 
 The unit tests run the same checks on a fixed corpus (see the "UBJSON round-trip
 invariants" test case), so keep both in sync.
@@ -29,8 +29,6 @@ drivers.
 */
 
 #include <cassert>
-#include <iostream>
-#include <sstream>
 #include <nlohmann/json.hpp>
 
 // the round-trip checks below are assertions; NDEBUG would compile them away

tests/src/round_trip_corpus.hpp

@@ -19,13 +19,14 @@
 
 #include <nlohmann/json.hpp>
 
-// Values for the round-trip property tests of the UBJSON and BJData writers.
+// Values for the round-trip property tests of the binary format writers
+// (BJData, BON8, BSON, CBOR, MessagePack and UBJSON).
 //
-// The fuzzer drivers (tests/src/fuzzer-parse_ubjson.cpp and
-// fuzzer-parse_bjdata.cpp) check that anything the library parses can be
-// serialized, parsed back, and serialized again without loss. Those checks
-// only run at OSS-Fuzz, so a regression used to surface days later as an
-// external report. The unit tests run the same checks on this corpus in CI.
+// The fuzzer drivers (tests/src/fuzzer-parse_*.cpp) check that anything the
+// library parses can be serialized, parsed back, and serialized again
+// without loss. Those checks only run at OSS-Fuzz, so a regression used to
+// surface days later as an external report. The unit tests run the same
+// checks on this corpus in CI.
 //
 // The corpus is deterministic: std::mt19937's output sequence is fixed by
 // the standard, and it is used directly rather than through a distribution

tests/src/sax_countdown.hpp

@@ -0,0 +1,99 @@
+//     __ _____ _____ _____
+//  __|  |   __|     |   | |  JSON for Modern C++ (supporting code)
+// |  |  |__   |  |  | | | |  version 3.12.0
+// |_____|_____|_____|_|___|  https://github.com/nlohmann/json
+//
+// SPDX-FileCopyrightText: 2013-2026 Niels Lohmann <https://nlohmann.me>
+// SPDX-License-Identifier: MIT
+
+#pragma once
+
+#include <cstddef>
+#include <cstdint>
+#include <string>
+#include <vector>
+
+#include <nlohmann/json.hpp>
+
+namespace utils
+{
+/// a SAX event consumer that stops accepting events after a fixed count,
+/// used by the binary-format tests to check behavior when the SAX consumer
+/// rejects an event partway through parsing
+class SaxCountdown
+{
+  public:
+    using json = nlohmann::json;
+
+    explicit SaxCountdown(const int count) : events_left(count)
+    {}
+
+    bool null()
+    {
+        return events_left-- > 0;
+    }
+
+    bool boolean(bool /*unused*/)
+    {
+        return events_left-- > 0;
+    }
+
+    bool number_integer(json::number_integer_t /*unused*/)
+    {
+        return events_left-- > 0;
+    }
+
+    bool number_unsigned(json::number_unsigned_t /*unused*/)
+    {
+        return events_left-- > 0;
+    }
+
+    bool number_float(json::number_float_t /*unused*/, const std::string& /*unused*/)
+    {
+        return events_left-- > 0;
+    }
+
+    bool string(std::string& /*unused*/)
+    {
+        return events_left-- > 0;
+    }
+
+    bool binary(std::vector<std::uint8_t>& /*unused*/)
+    {
+        return events_left-- > 0;
+    }
+
+    bool start_object(std::size_t /*unused*/)
+    {
+        return events_left-- > 0;
+    }
+
+    bool key(std::string& /*unused*/)
+    {
+        return events_left-- > 0;
+    }
+
+    bool end_object()
+    {
+        return events_left-- > 0;
+    }
+
+    bool start_array(std::size_t /*unused*/)
+    {
+        return events_left-- > 0;
+    }
+
+    bool end_array()
+    {
+        return events_left-- > 0;
+    }
+
+    bool parse_error(std::size_t /*unused*/, const std::string& /*unused*/, const json::exception& /*unused*/) // NOLINT(readability-convert-member-functions-to-static)
+    {
+        return false;
+    }
+
+  private:
+    int events_left = 0;
+};
+} // namespace utils

tests/src/unit-32bit.cpp

@@ -12,80 +12,11 @@
 using nlohmann::json;
 
 #include <climits> // SIZE_MAX
-#include <limits> // numeric_limits
 
-template <typename OfType, typename T, bool MinInRange, bool MaxInRange>
-struct trait_test_arg
-{
-    using of_type = OfType;
-    using type = T;
-    static constexpr bool min_in_range = MinInRange;
-    static constexpr bool max_in_range = MaxInRange;
-};
-
-TEST_CASE_TEMPLATE_DEFINE("value_in_range_of trait", T, value_in_range_of_test) // NOLINT(readability-math-missing-parentheses)
-{
-    using nlohmann::detail::value_in_range_of;
-
-    using of_type = typename T::of_type;
-    using type = typename T::type;
-    constexpr bool min_in_range = T::min_in_range;
-    constexpr bool max_in_range = T::max_in_range;
-
-    type const val_min = std::numeric_limits<type>::min();
-    type const val_min2 = val_min + 1;
-    type const val_max = std::numeric_limits<type>::max();
-    type const val_max2 = val_max - 1;
-
-    REQUIRE(CHAR_BIT == 8);
-
-    std::string of_type_str;
-    if (std::is_unsigned<of_type>::value)
-    {
-        of_type_str += "u";
-    }
-    of_type_str += "int";
-    of_type_str += std::to_string(sizeof(of_type) * 8);
-
-    INFO("of_type := ", of_type_str);
-
-    std::string type_str;
-    if (std::is_unsigned<type>::value)
-    {
-        type_str += "u";
-    }
-    type_str += "int";
-    type_str += std::to_string(sizeof(type) * 8);
-
-    INFO("type := ", type_str);
-
-    CAPTURE(val_min);
-    CAPTURE(min_in_range);
-    CAPTURE(val_max);
-    CAPTURE(max_in_range);
-
-    if (min_in_range)
-    {
-        CHECK(value_in_range_of<of_type>(val_min));
-        CHECK(value_in_range_of<of_type>(val_min2));
-    }
-    else
-    {
-        CHECK_FALSE(value_in_range_of<of_type>(val_min));
-        CHECK_FALSE(value_in_range_of<of_type>(val_min2));
-    }
-
-    if (max_in_range)
-    {
-        CHECK(value_in_range_of<of_type>(val_max));
-        CHECK(value_in_range_of<of_type>(val_max2));
-    }
-    else
-    {
-        CHECK_FALSE(value_in_range_of<of_type>(val_max));
-        CHECK_FALSE(value_in_range_of<of_type>(val_max2));
-    }
-}
+// JSON_32bitTest=ONLY builds only this file, so it must keep its own
+// include of the shared trait/TEST_CASE_TEMPLATE_DEFINE rather than relying
+// on unit-bjdata.cpp to provide it
+#include "value_in_range_of_test.hpp"
 
 TEST_CASE("32bit")
 {

tests/src/unit-allocator.cpp

@@ -239,7 +239,7 @@ TEST_CASE("controlled bad_alloc")
             // iterative path instead, part-way through its worklist.
             const auto check_deep_copy = [](bool objects)
             {
-                CAPTURE(objects);
+                CAPTURE(objects)
 
                 next_construct_fails = false;
 
@@ -315,7 +315,7 @@ struct nth_alloc_fails_allocator : std::allocator<T>
 template<class BasicJsonType>
 void check_deep_copy_survives_failing_allocation(bool nest_objects)
 {
-    CAPTURE(nest_objects);
+    CAPTURE(nest_objects)
 
     fail_at_alloc_call = -1;
 
@@ -352,7 +352,7 @@ void check_deep_copy_survives_failing_allocation(bool nest_objects)
     // must come out exactly as it went in
     for (std::size_t n = 0; n < total_allocations; ++n)
     {
-        CAPTURE(n);
+        CAPTURE(n)
         alloc_call_count = 0;
         fail_at_alloc_call = static_cast<long>(n);
 

tests/src/unit-assert_macro.cpp

@@ -18,7 +18,7 @@ DOCTEST_CLANG_SUPPRESS_WARNING("-Wstrict-overflow")
 static int assert_counter;
 
 /// set failure variable to true instead of calling assert(x)
-#define JSON_ASSERT(x) {if (!(x)) ++assert_counter; }
+#define JSON_ASSERT(x) do { if (!(x)) { ++assert_counter; } } while (false)
 
 #include <nlohmann/json.hpp>
 using nlohmann::json;

tests/src/unit-binary_writer_sinks.cpp

@@ -89,7 +89,7 @@ TEST_CASE("binary writer output sinks")
         // the first iteration
         for (const auto& j : test_values())
         {
-            CAPTURE(j.dump(-1, ' ', false, json::error_handler_t::replace));
+            CAPTURE(j.dump(-1, ' ', false, json::error_handler_t::replace))
 
             std::vector<std::uint8_t> cbor;
             json::to_cbor(j, cbor);
@@ -120,8 +120,8 @@ TEST_CASE("binary writer output sinks")
                     {
                         continue; // not a supported combination
                     }
-                    CAPTURE(use_size);
-                    CAPTURE(use_type);
+                    CAPTURE(use_size)
+                    CAPTURE(use_type)
                     std::vector<std::uint8_t> ubjson;
                     json::to_ubjson(j, ubjson, use_size, use_type);
                     CHECK(json::to_ubjson(j, use_size, use_type) == ubjson);
@@ -141,7 +141,7 @@ TEST_CASE("binary writer output sinks")
 
         for (const auto& j : bson_values())
         {
-            CAPTURE(j.dump());
+            CAPTURE(j.dump())
             std::vector<std::uint8_t> bson;
             json::to_bson(j, bson);
             CHECK(json::to_bson(j) == bson);
@@ -152,7 +152,7 @@ TEST_CASE("binary writer output sinks")
     {
         for (const auto& j : test_values())
         {
-            CAPTURE(j.dump(-1, ' ', false, json::error_handler_t::replace));
+            CAPTURE(j.dump(-1, ' ', false, json::error_handler_t::replace))
 
             const std::vector<std::uint8_t> expected = json::to_cbor(j);
             std::vector<char> as_char;
@@ -177,7 +177,7 @@ TEST_CASE("binary_reserve_hint never over-reserves")
 {
     for (const auto& j : test_values())
     {
-        CAPTURE(j.dump(-1, ' ', false, json::error_handler_t::replace));
+        CAPTURE(j.dump(-1, ' ', false, json::error_handler_t::replace))
 
         const std::size_t hint = nlohmann::detail::binary_reserve_hint(j);
 
@@ -194,7 +194,7 @@ TEST_CASE("binary_reserve_hint never over-reserves")
 
     for (const auto& j : bson_values())
     {
-        CAPTURE(j.dump());
+        CAPTURE(j.dump())
         CHECK(nlohmann::detail::binary_reserve_hint(j) <= json::to_bson(j).size());
     }
 

tests/src/unit-bjdata.cpp

@@ -21,158 +21,13 @@ using nlohmann::json;
 #include "make_test_data_available.hpp"
 #include "round_trip_corpus.hpp"
 #include "test_utils.hpp"
+#include "sax_countdown.hpp"
+using utils::SaxCountdown;
 
-namespace
-{
-class SaxCountdown
-{
-  public:
-    explicit SaxCountdown(const int count) : events_left(count)
-    {}
 
-    bool null()
-    {
-        return events_left-- > 0;
-    }
-
-    bool boolean(bool /*unused*/)
-    {
-        return events_left-- > 0;
-    }
-
-    bool number_integer(json::number_integer_t /*unused*/)
-    {
-        return events_left-- > 0;
-    }
-
-    bool number_unsigned(json::number_unsigned_t /*unused*/)
-    {
-        return events_left-- > 0;
-    }
-
-    bool number_float(json::number_float_t /*unused*/, const std::string& /*unused*/)
-    {
-        return events_left-- > 0;
-    }
-
-    bool string(std::string& /*unused*/)
-    {
-        return events_left-- > 0;
-    }
-
-    bool binary(std::vector<std::uint8_t>& /*unused*/)
-    {
-        return events_left-- > 0;
-    }
-
-    bool start_object(std::size_t /*unused*/)
-    {
-        return events_left-- > 0;
-    }
-
-    bool key(std::string& /*unused*/)
-    {
-        return events_left-- > 0;
-    }
-
-    bool end_object()
-    {
-        return events_left-- > 0;
-    }
-
-    bool start_array(std::size_t /*unused*/)
-    {
-        return events_left-- > 0;
-    }
-
-    bool end_array()
-    {
-        return events_left-- > 0;
-    }
-
-    bool parse_error(std::size_t /*unused*/, const std::string& /*unused*/, const json::exception& /*unused*/) // NOLINT(readability-convert-member-functions-to-static)
-    {
-        return false;
-    }
-
-  private:
-    int events_left = 0;
-};
-} // namespace
-
-// at some point in the future, a unit test dedicated to type traits might be a good idea
-template <typename OfType, typename T, bool MinInRange, bool MaxInRange>
-struct trait_test_arg
-{
-    using of_type = OfType;
-    using type = T;
-    static constexpr bool min_in_range = MinInRange;
-    static constexpr bool max_in_range = MaxInRange;
-};
-
-TEST_CASE_TEMPLATE_DEFINE("value_in_range_of trait", T, value_in_range_of_test) // NOLINT(readability-math-missing-parentheses)
-{
-    using nlohmann::detail::value_in_range_of;
-
-    using of_type = typename T::of_type;
-    using type = typename T::type;
-    constexpr bool min_in_range = T::min_in_range;
-    constexpr bool max_in_range = T::max_in_range;
-
-    type const val_min = std::numeric_limits<type>::min();
-    type const val_min2 = val_min + 1;
-    type const val_max = std::numeric_limits<type>::max();
-    type const val_max2 = val_max - 1;
-
-    REQUIRE(CHAR_BIT == 8);
-
-    std::string of_type_str;
-    if (std::is_unsigned<of_type>::value)
-    {
-        of_type_str += "u";
-    }
-    of_type_str += "int";
-    of_type_str += std::to_string(sizeof(of_type) * 8);
-
-    INFO("of_type := ", of_type_str);
-
-    std::string type_str;
-    if (std::is_unsigned<type>::value)
-    {
-        type_str += "u";
-    }
-    type_str += "int";
-    type_str += std::to_string(sizeof(type) * 8);
-
-    INFO("type := ", type_str);
-
-    CAPTURE(val_min);
-    CAPTURE(min_in_range);
-    CAPTURE(val_max);
-    CAPTURE(max_in_range);
-
-    if (min_in_range)
-    {
-        CHECK(value_in_range_of<of_type>(val_min));
-        CHECK(value_in_range_of<of_type>(val_min2));
-    }
-    else
-    {
-        CHECK_FALSE(value_in_range_of<of_type>(val_min));
-        CHECK_FALSE(value_in_range_of<of_type>(val_min2));
-    }
-
-    if (max_in_range)
-    {
-        CHECK(value_in_range_of<of_type>(val_max));
-        CHECK(value_in_range_of<of_type>(val_max2));
-    }
-    else
-    {
-        CHECK_FALSE(value_in_range_of<of_type>(val_max));
-        CHECK_FALSE(value_in_range_of<of_type>(val_max2));
-    }
-}
+// trait_test_arg and the "value_in_range_of trait" TEST_CASE_TEMPLATE_DEFINE
+// are shared with unit-32bit.cpp
+#include "value_in_range_of_test.hpp"
 
 // NOLINTNEXTLINE(bugprone-throwing-static-initialization)
 TEST_CASE_TEMPLATE_INVOKE(value_in_range_of_test, \
@@ -2668,7 +2523,7 @@ TEST_CASE("BJData")
                         {"uint8", "int8", "uint16", "int16", "uint32", "int32", "uint64", "int64", "char"
                         })
                 {
-                    CAPTURE(type);
+                    CAPTURE(type)
                     const std::string text = std::string(R"({"_ArrayType_":")") + type +
                                              R"(","_ArraySize_":[2,3],"_ArrayData_":[1,2,3,4,5,6]})";
                     const auto from_text = json::to_bjdata(json::parse(text));
@@ -2976,7 +2831,7 @@ TEST_CASE("BJData")
                             R"({"_ArrayType_":"int16","_ArraySize_":[0,2],"_ArrayData_":[]})"
                         })
                 {
-                    CAPTURE(text);
+                    CAPTURE(text)
                     const json j = json::parse(text);
                     for (const bool use_size :
                             {
@@ -3010,7 +2865,7 @@ TEST_CASE("BJData")
                             R"({"_ArrayType_":"int16","_ArraySize_":[],"_ArrayData_":null})"
                         })
                 {
-                    CAPTURE(text);
+                    CAPTURE(text)
                     const json j = json::parse(text);
                     const auto out = json::to_bjdata(j);
                     CHECK(out.at(0) == '{');
@@ -4052,6 +3907,41 @@ TEST_CASE("Universal Binary JSON Specification Examples 1")
             CHECK(json::to_bjdata(j) == v);
             CHECK(json::from_bjdata(v) == j);
         }
+
+        SECTION("ill-formed UTF-8 (see #5529, #5651)")
+        {
+            // none of the binary format specs requires a decoder to reject
+            // ill-formed UTF-8 in a text string, so a value whose bytes are
+            // not valid UTF-8 (0xC0 0xAE is an overlong encoding of '.')
+            // round-trips byte for byte as a string value; to_bjdata() is
+            // strict, so such a value cannot be written back
+            const std::vector<uint8_t> v = {'S', 'i', 2, 0xc0, 0xae};
+            json j;
+            CHECK_NOTHROW(j = json::from_bjdata(v));
+            REQUIRE(j.is_string());
+            CHECK(j.get_ref<const json::string_t&>() == std::string("\xc0\xae"));
+            CHECK_THROWS_AS(j.dump(), json::type_error&);
+            CHECK_THROWS_AS(json::to_bjdata(j), json::type_error&);
+
+            // the same bytes as an object key round-trip as well
+            const std::vector<uint8_t> v_key = {'{', 'i', 2, 0xc0, 0xae, 'i', 1, '}'};
+            json j_key;
+            CHECK_NOTHROW(j_key = json::from_bjdata(v_key));
+            REQUIRE(j_key.is_object());
+            CHECK(j_key.contains(std::string("\xc0\xae")));
+            CHECK_THROWS_AS(json::to_bjdata(j_key), json::type_error&);
+
+            CHECK_THROWS_WITH_AS(json::to_bjdata(json("\xFF")), "[json.exception.type_error.316] invalid UTF-8 byte at index 0: 0xFF", json::type_error&);
+            // a truncated multi-byte sequence
+            CHECK_THROWS_WITH_AS(json::to_bjdata(json("\xC3")), "[json.exception.type_error.316] invalid UTF-8 byte at index 0: 0xC3", json::type_error&);
+            // an encoded surrogate half (U+D800)
+            CHECK_THROWS_WITH_AS(json::to_bjdata(json("\xED\xA0\x80")), "[json.exception.type_error.316] invalid UTF-8 byte at index 0: 0xED", json::type_error&);
+            // an overlong encoding of '.'
+            CHECK_THROWS_WITH_AS(json::to_bjdata(json("\xC0\xAF")), "[json.exception.type_error.316] invalid UTF-8 byte at index 0: 0xC0", json::type_error&);
+
+            // an object key with ill-formed UTF-8 is rejected the same way
+            CHECK_THROWS_WITH_AS(json::to_bjdata(json{{"\xFF", 1}}), "[json.exception.type_error.316] invalid UTF-8 byte at index 0: 0xFF", json::type_error&);
+        }
     }
 
     SECTION("Array Type")
@@ -4344,7 +4234,7 @@ TEST_CASE("BJData and UBJSON can be written to a string")
 
     for (const auto& j : values)
     {
-        CAPTURE(j.dump());
+        CAPTURE(j.dump())
         for (const bool use_size :
                 {
                     false, true
@@ -4359,8 +4249,8 @@ TEST_CASE("BJData and UBJSON can be written to a string")
                 {
                     continue;
                 }
-                CAPTURE(use_size);
-                CAPTURE(use_type);
+                CAPTURE(use_size)
+                CAPTURE(use_type)
 
                 const auto bjdata = json::to_bjdata(j, use_size, use_type);
                 std::string bjdata_string;

tests/src/unit-bon8.cpp

@@ -21,85 +21,13 @@ using nlohmann::json;
 #include <string>
 #include <vector>
 #include "make_test_data_available.hpp"
+#include "round_trip_corpus.hpp"
 #include "test_utils.hpp"
+#include "sax_countdown.hpp"
+using utils::SaxCountdown;
 
 namespace
 {
-class SaxCountdown
-{
-  public:
-    explicit SaxCountdown(const int count) : events_left(count)
-    {}
-
-    bool null()
-    {
-        return events_left-- > 0;
-    }
-
-    bool boolean(bool /*unused*/)
-    {
-        return events_left-- > 0;
-    }
-
-    bool number_integer(json::number_integer_t /*unused*/)
-    {
-        return events_left-- > 0;
-    }
-
-    bool number_unsigned(json::number_unsigned_t /*unused*/)
-    {
-        return events_left-- > 0;
-    }
-
-    bool number_float(json::number_float_t /*unused*/, const std::string& /*unused*/)
-    {
-        return events_left-- > 0;
-    }
-
-    bool string(std::string& /*unused*/)
-    {
-        return events_left-- > 0;
-    }
-
-    bool binary(std::vector<std::uint8_t>& /*unused*/)
-    {
-        return events_left-- > 0;
-    }
-
-    bool start_object(std::size_t /*unused*/)
-    {
-        return events_left-- > 0;
-    }
-
-    bool key(std::string& /*unused*/)
-    {
-        return events_left-- > 0;
-    }
-
-    bool end_object()
-    {
-        return events_left-- > 0;
-    }
-
-    bool start_array(std::size_t /*unused*/)
-    {
-        return events_left-- > 0;
-    }
-
-    bool end_array()
-    {
-        return events_left-- > 0;
-    }
-
-    bool parse_error(std::size_t /*unused*/, const std::string& /*unused*/, const json::exception& /*unused*/) // NOLINT(readability-convert-member-functions-to-static)
-    {
-        return false;
-    }
-
-  private:
-    int events_left = 0;
-};
-
 using bytes = std::vector<std::uint8_t>;
 
 /// @return the string with the given bytes
@@ -817,6 +745,39 @@ TEST_CASE("Parse BON8 directly from a file using iterator and sentinel")
     CHECK((parsed.is_object() || parsed.is_array()));
 }
 
+TEST_CASE("BON8 round-trip invariants")
+{
+    // This checks what the parse_bon8_fuzzer driver checks (see
+    // tests/src/fuzzer-parse_bon8.cpp), so that a regression shows up in CI
+    // rather than as an OSS-Fuzz report: anything from_bon8() returns (j1)
+    // can be serialized, parsed back (j2), and serialized again to reproduce
+    // the exact bytes. The stream-versus-contiguous input check the driver
+    // also performs is not covered here (see #5601).
+    for (const auto& j0 : utils::round_trip_corpus::values())
+    {
+        json j1;
+        try
+        {
+            // turn the corpus value into a value as from_bon8() returns it
+            j1 = json::from_bon8(json::to_bon8(j0));
+        }
+        catch (const json::exception&)
+        {
+            // BON8 cannot represent an unsigned integer above INT64_MAX, and
+            // the fuzzer driver only ever sees values from_bon8() actually
+            // produced, so skip such corpus values here, too
+            continue;
+        }
+
+        INFO("j1 = " << j1.dump());
+        const std::vector<std::uint8_t> vec = json::to_bon8(j1);
+        json j2;
+        // anything the library writes must be parsable by the library
+        REQUIRE_NOTHROW(j2 = json::from_bon8(vec));
+        CHECK(json::to_bon8(j2) == vec);
+    }
+}
+
 TEST_CASE("BON8 roundtrips" * doctest::skip())
 {
     SECTION("input from HikoGUI")

tests/src/unit-bson.cpp

@@ -17,7 +17,10 @@ using nlohmann::json;
 #include <sstream>
 #include <vector>
 #include "make_test_data_available.hpp"
+#include "round_trip_corpus.hpp"
 #include "test_utils.hpp"
+#include "sax_countdown.hpp"
+using utils::SaxCountdown;
 
 namespace
 {
@@ -151,6 +154,51 @@ TEST_CASE("BSON")
 #endif
     }
 
+    SECTION("ill-formed UTF-8 (see #5529, #5651)")
+    {
+        // a BSON document {"s": "\xC0\xAE"} (0xC0 0xAE is an overlong
+        // encoding of '.'); the BSON spec does not require a decoder to
+        // reject ill-formed UTF-8 in a string value, so the reader hands the
+        // bytes back unchanged
+        const std::vector<uint8_t> v =
+        {
+            0x0F, 0x00, 0x00, 0x00, // document length
+            0x02, 's', 0x00,        // type 0x02 (string), key "s"
+            0x03, 0x00, 0x00, 0x00, // string length (including null)
+            0xc0, 0xae, 0x00,       // string content and its null terminator
+            0x00                    // document terminator
+        };
+        json j;
+        CHECK_NOTHROW(j = json::from_bson(v));
+        REQUIRE(j.is_object());
+        REQUIRE(j.contains("s"));
+        CHECK(j["s"].get_ref<const json::string_t&>() == std::string("\xc0\xae"));
+        // dump() still requires valid UTF-8 and throws for such a value
+        CHECK_THROWS_AS(j.dump(), json::type_error&);
+        // to_bson() is strict as well, so the value cannot be written back
+        CHECK_THROWS_AS(json::to_bson(j), json::type_error&);
+
+        // to_bson() rejects the same kind of ill-formed string value, before
+        // any bytes reach the output adapter (the BSON document length
+        // prefix must be known up front, so nothing is written incrementally)
+        std::vector<std::uint8_t> out{0x42}; // a sentinel byte the writer must not touch
+        CHECK_THROWS_WITH_AS(json::to_bson(json{{"s", "\xFF"}}, nlohmann::detail::output_adapter<std::uint8_t>(out)), "[json.exception.type_error.316] invalid UTF-8 byte at index 0: 0xFF", json::type_error&);
+        CHECK(out == std::vector<std::uint8_t> {0x42});
+
+        CHECK_THROWS_WITH_AS(json::to_bson(json{{"s", "\xFF"}}), "[json.exception.type_error.316] invalid UTF-8 byte at index 0: 0xFF", json::type_error&);
+        // a truncated multi-byte sequence
+        CHECK_THROWS_WITH_AS(json::to_bson(json{{"s", "\xC3"}}), "[json.exception.type_error.316] invalid UTF-8 byte at index 0: 0xC3", json::type_error&);
+        // an encoded surrogate half (U+D800)
+        CHECK_THROWS_WITH_AS(json::to_bson(json{{"s", "\xED\xA0\x80"}}), "[json.exception.type_error.316] invalid UTF-8 byte at index 0: 0xED", json::type_error&);
+        // an overlong encoding of '.'
+        CHECK_THROWS_WITH_AS(json::to_bson(json{{"s", "\xC0\xAF"}}), "[json.exception.type_error.316] invalid UTF-8 byte at index 0: 0xC0", json::type_error&);
+
+        // an object key with ill-formed UTF-8 is rejected as well; unlike
+        // the reader (which never validates element names), the writer
+        // checks both string values and object keys
+        CHECK_THROWS_WITH_AS(json::to_bson(json{{"\xFF", 1}}), "[json.exception.type_error.316] invalid UTF-8 byte at index 0: 0xFF", json::type_error&);
+    }
+
     SECTION("lengths exceeding INT32_MAX cannot be serialized to BSON")
     {
         // out_of_range.412 is thrown from a single shared helper
@@ -861,83 +909,6 @@ TEST_CASE("BSON input/output_adapters")
     }
 }
 
-namespace
-{
-class SaxCountdown
-{
-  public:
-    explicit SaxCountdown(const int count) : events_left(count)
-    {}
-
-    bool null()
-    {
-        return events_left-- > 0;
-    }
-
-    bool boolean(bool /*unused*/)
-    {
-        return events_left-- > 0;
-    }
-
-    bool number_integer(json::number_integer_t /*unused*/)
-    {
-        return events_left-- > 0;
-    }
-
-    bool number_unsigned(json::number_unsigned_t /*unused*/)
-    {
-        return events_left-- > 0;
-    }
-
-    bool number_float(json::number_float_t /*unused*/, const std::string& /*unused*/)
-    {
-        return events_left-- > 0;
-    }
-
-    bool string(std::string& /*unused*/)
-    {
-        return events_left-- > 0;
-    }
-
-    bool binary(std::vector<std::uint8_t>& /*unused*/)
-    {
-        return events_left-- > 0;
-    }
-
-    bool start_object(std::size_t /*unused*/)
-    {
-        return events_left-- > 0;
-    }
-
-    bool key(std::string& /*unused*/)
-    {
-        return events_left-- > 0;
-    }
-
-    bool end_object()
-    {
-        return events_left-- > 0;
-    }
-
-    bool start_array(std::size_t /*unused*/)
-    {
-        return events_left-- > 0;
-    }
-
-    bool end_array()
-    {
-        return events_left-- > 0;
-    }
-
-    bool parse_error(std::size_t /*unused*/, const std::string& /*unused*/, const json::exception& /*unused*/) // NOLINT(readability-convert-member-functions-to-static)
-    {
-        return false;
-    }
-
-  private:
-    int events_left = 0;
-};
-} // namespace
 
 TEST_CASE("Incomplete BSON Input")
 {
@@ -1692,6 +1663,44 @@ TEST_CASE("Parse BSON directly from a file using iterator and sentinel")
     CHECK(parsed == expected);
 }
 
+TEST_CASE("BSON round-trip invariants")
+{
+    // This checks what the parse_bson_fuzzer driver checks (see
+    // tests/src/fuzzer-parse_bson.cpp), so that a regression shows up in CI
+    // rather than as an OSS-Fuzz report: anything from_bson() returns (j1)
+    // can be serialized, parsed back (j2), and serialized again to reproduce
+    // the exact bytes. BSON only serializes objects, so non-object corpus
+    // values are skipped.
+    for (const auto& j0 : utils::round_trip_corpus::values())
+    {
+        if (!j0.is_object())
+        {
+            continue;
+        }
+
+        json j1;
+        try
+        {
+            // turn the corpus value into a value as from_bson() returns it
+            j1 = json::from_bson(json::to_bson(j0));
+        }
+        catch (const json::exception&)
+        {
+            // the fuzzer driver only ever sees values from_bson() actually
+            // produced, so skip corpus values that do not survive the
+            // round trip here, too
+            continue;
+        }
+
+        INFO("j1 = " << j1.dump());
+        const std::vector<std::uint8_t> vec = json::to_bson(j1);
+        json j2;
+        // anything the library writes must be parsable by the library
+        REQUIRE_NOTHROW(j2 = json::from_bson(vec));
+        CHECK(json::to_bson(j2) == vec);
+    }
+}
+
 TEST_CASE("BSON roundtrips" * doctest::skip())
 {
     SECTION("reference files")
@@ -1788,7 +1797,7 @@ TEST_CASE("BSON: deeply nested values")
         json value = "leaf";
         for (std::size_t depth = 0; depth <= 300; ++depth)
         {
-            CAPTURE(depth);
+            CAPTURE(depth)
             const json document = {{"value", value}, {"n", depth}};
             CHECK(json::from_bson(json::to_bson(document)) == document);
 
@@ -1836,7 +1845,7 @@ value = depth % 2 == 0 ? json{{"a", std::move(value)}, {"b", {1, "x"}}} :
                     false, true
                 })
         {
-            CAPTURE(objects);
+            CAPTURE(objects)
             std::string text = "{\"a\":";
             for (std::size_t i = 0; i < depth; ++i)
             {

tests/src/unit-capacity.cpp

@@ -17,7 +17,7 @@ TEST_CASE("capacity")
     {
         SECTION("boolean")
         {
-            json j = true; // NOLINT(misc-const-correctness)
+            json j = true;
             const json j_const = true;
 
             SECTION("result of empty")
@@ -35,7 +35,7 @@ TEST_CASE("capacity")
 
         SECTION("string")
         {
-            json j = "hello world"; // NOLINT(misc-const-correctness)
+            json j = "hello world";
             const json j_const = "hello world";
 
             SECTION("result of empty")
@@ -55,7 +55,7 @@ TEST_CASE("capacity")
         {
             SECTION("empty array")
             {
-                json j = json::array(); // NOLINT(misc-const-correctness)
+                json j = json::array();
                 const json j_const = json::array();
 
                 SECTION("result of empty")
@@ -73,7 +73,7 @@ TEST_CASE("capacity")
 
             SECTION("filled array")
             {
-                json j = {1, 2, 3}; // NOLINT(misc-const-correctness)
+                json j = {1, 2, 3};
                 const json j_const = {1, 2, 3};
 
                 SECTION("result of empty")
@@ -94,7 +94,7 @@ TEST_CASE("capacity")
         {
             SECTION("empty object")
             {
-                json j = json::object(); // NOLINT(misc-const-correctness)
+                json j = json::object();
                 const json j_const = json::object();
 
                 SECTION("result of empty")
@@ -112,7 +112,7 @@ TEST_CASE("capacity")
 
             SECTION("filled object")
             {
-                json j = {{"one", 1}, {"two", 2}, {"three", 3}}; // NOLINT(misc-const-correctness)
+                json j = {{"one", 1}, {"two", 2}, {"three", 3}};
                 const json j_const = {{"one", 1}, {"two", 2}, {"three", 3}};
 
                 SECTION("result of empty")
@@ -131,7 +131,7 @@ TEST_CASE("capacity")
 
         SECTION("number (integer)")
         {
-            json j = -23; // NOLINT(misc-const-correctness)
+            json j = -23;
             const json j_const = -23;
 
             SECTION("result of empty")
@@ -149,7 +149,7 @@ TEST_CASE("capacity")
 
         SECTION("number (unsigned)")
         {
-            json j = 23u; // NOLINT(misc-const-correctness)
+            json j = 23u;
             const json j_const = 23u;
 
             SECTION("result of empty")
@@ -167,7 +167,7 @@ TEST_CASE("capacity")
 
         SECTION("number (float)")
         {
-            json j = 23.42; // NOLINT(misc-const-correctness)
+            json j = 23.42;
             const json j_const = 23.42;
 
             SECTION("result of empty")
@@ -185,7 +185,7 @@ TEST_CASE("capacity")
 
         SECTION("null")
         {
-            json j = nullptr; // NOLINT(misc-const-correctness)
+            json j = nullptr;
             const json j_const = nullptr;
 
             SECTION("result of empty")
@@ -206,7 +206,7 @@ TEST_CASE("capacity")
     {
         SECTION("boolean")
         {
-            json j = true; // NOLINT(misc-const-correctness)
+            json j = true;
             const json j_const = true;
 
             SECTION("result of size")
@@ -226,7 +226,7 @@ TEST_CASE("capacity")
 
         SECTION("string")
         {
-            json j = "hello world"; // NOLINT(misc-const-correctness)
+            json j = "hello world";
             const json j_const = "hello world";
 
             SECTION("result of size")
@@ -248,7 +248,7 @@ TEST_CASE("capacity")
         {
             SECTION("empty array")
             {
-                json j = json::array(); // NOLINT(misc-const-correctness)
+                json j = json::array();
                 const json j_const = json::array();
 
                 SECTION("result of size")
@@ -268,7 +268,7 @@ TEST_CASE("capacity")
 
             SECTION("filled array")
             {
-                json j = {1, 2, 3}; // NOLINT(misc-const-correctness)
+                json j = {1, 2, 3};
                 const json j_const = {1, 2, 3};
 
                 SECTION("result of size")
@@ -291,7 +291,7 @@ TEST_CASE("capacity")
         {
             SECTION("empty object")
             {
-                json j = json::object(); // NOLINT(misc-const-correctness)
+                json j = json::object();
                 const json j_const = json::object();
 
                 SECTION("result of size")
@@ -311,7 +311,7 @@ TEST_CASE("capacity")
 
             SECTION("filled object")
             {
-                json j = {{"one", 1}, {"two", 2}, {"three", 3}}; // NOLINT(misc-const-correctness)
+                json j = {{"one", 1}, {"two", 2}, {"three", 3}};
                 const json j_const = {{"one", 1}, {"two", 2}, {"three", 3}};
 
                 SECTION("result of size")
@@ -332,7 +332,7 @@ TEST_CASE("capacity")
 
         SECTION("number (integer)")
         {
-            json j = -23; // NOLINT(misc-const-correctness)
+            json j = -23;
             const json j_const = -23;
 
             SECTION("result of size")
@@ -352,7 +352,7 @@ TEST_CASE("capacity")
 
         SECTION("number (unsigned)")
         {
-            json j = 23u; // NOLINT(misc-const-correctness)
+            json j = 23u;
             const json j_const = 23u;
 
             SECTION("result of size")
@@ -372,7 +372,7 @@ TEST_CASE("capacity")
 
         SECTION("number (float)")
         {
-            json j = 23.42; // NOLINT(misc-const-correctness)
+            json j = 23.42;
             const json j_const = 23.42;
 
             SECTION("result of size")
@@ -392,7 +392,7 @@ TEST_CASE("capacity")
 
         SECTION("null")
         {
-            json j = nullptr; // NOLINT(misc-const-correctness)
+            json j = nullptr;
             const json j_const = nullptr;
 
             SECTION("result of size")
@@ -415,7 +415,7 @@ TEST_CASE("capacity")
     {
         SECTION("boolean")
         {
-            json j = true; // NOLINT(misc-const-correctness)
+            json j = true;
             const json j_const = true;
 
             SECTION("result of max_size")
@@ -427,7 +427,7 @@ TEST_CASE("capacity")
 
         SECTION("string")
         {
-            json j = "hello world"; // NOLINT(misc-const-correctness)
+            json j = "hello world";
             const json j_const = "hello world";
 
             SECTION("result of max_size")
@@ -441,7 +441,7 @@ TEST_CASE("capacity")
         {
             SECTION("empty array")
             {
-                json j = json::array(); // NOLINT(misc-const-correctness)
+                json j = json::array();
                 const json j_const = json::array();
 
                 SECTION("result of max_size")
@@ -453,7 +453,7 @@ TEST_CASE("capacity")
 
             SECTION("filled array")
             {
-                json j = {1, 2, 3}; // NOLINT(misc-const-correctness)
+                json j = {1, 2, 3};
                 const json j_const = {1, 2, 3};
 
                 SECTION("result of max_size")
@@ -468,7 +468,7 @@ TEST_CASE("capacity")
         {
             SECTION("empty object")
             {
-                json j = json::object(); // NOLINT(misc-const-correctness)
+                json j = json::object();
                 const json j_const = json::object();
 
                 SECTION("result of max_size")
@@ -480,7 +480,7 @@ TEST_CASE("capacity")
 
             SECTION("filled object")
             {
-                json j = {{"one", 1}, {"two", 2}, {"three", 3}}; // NOLINT(misc-const-correctness)
+                json j = {{"one", 1}, {"two", 2}, {"three", 3}};
                 const json j_const = {{"one", 1}, {"two", 2}, {"three", 3}};
 
                 SECTION("result of max_size")
@@ -493,7 +493,7 @@ TEST_CASE("capacity")
 
         SECTION("number (integer)")
         {
-            json j = -23; // NOLINT(misc-const-correctness)
+            json j = -23;
             const json j_const = -23;
 
             SECTION("result of max_size")
@@ -505,7 +505,7 @@ TEST_CASE("capacity")
 
         SECTION("number (unsigned)")
         {
-            json j = 23u; // NOLINT(misc-const-correctness)
+            json j = 23u;
             const json j_const = 23u;
 
             SECTION("result of max_size")
@@ -517,7 +517,7 @@ TEST_CASE("capacity")
 
         SECTION("number (float)")
         {
-            json j = 23.42; // NOLINT(misc-const-correctness)
+            json j = 23.42;
             const json j_const = 23.42;
 
             SECTION("result of max_size")
@@ -529,7 +529,7 @@ TEST_CASE("capacity")
 
         SECTION("null")
         {
-            json j = nullptr; // NOLINT(misc-const-correctness)
+            json j = nullptr;
             const json j_const = nullptr;
 
             SECTION("result of max_size")

tests/src/unit-cbor.cpp

@@ -18,85 +18,11 @@ using nlohmann::json;
 #include <list>
 #include <set>
 #include "make_test_data_available.hpp"
+#include "round_trip_corpus.hpp"
 #include "test_utils.hpp"
+#include "sax_countdown.hpp"
+using utils::SaxCountdown;
 
-namespace
-{
-class SaxCountdown
-{
-  public:
-    explicit SaxCountdown(const int count) : events_left(count)
-    {}
-
-    bool null()
-    {
-        return events_left-- > 0;
-    }
-
-    bool boolean(bool /*unused*/)
-    {
-        return events_left-- > 0;
-    }
-
-    bool number_integer(json::number_integer_t /*unused*/)
-    {
-        return events_left-- > 0;
-    }
-
-    bool number_unsigned(json::number_unsigned_t /*unused*/)
-    {
-        return events_left-- > 0;
-    }
-
-    bool number_float(json::number_float_t /*unused*/, const std::string& /*unused*/)
-    {
-        return events_left-- > 0;
-    }
-
-    bool string(std::string& /*unused*/)
-    {
-        return events_left-- > 0;
-    }
-
-    bool binary(std::vector<std::uint8_t>& /*unused*/)
-    {
-        return events_left-- > 0;
-    }
-
-    bool start_object(std::size_t /*unused*/)
-    {
-        return events_left-- > 0;
-    }
-
-    bool key(std::string& /*unused*/)
-    {
-        return events_left-- > 0;
-    }
-
-    bool end_object()
-    {
-        return events_left-- > 0;
-    }
-
-    bool start_array(std::size_t /*unused*/)
-    {
-        return events_left-- > 0;
-    }
-
-    bool end_array()
-    {
-        return events_left-- > 0;
-    }
-
-    bool parse_error(std::size_t /*unused*/, const std::string& /*unused*/, const json::exception& /*unused*/) // NOLINT(readability-convert-member-functions-to-static)
-    {
-        return false;
-    }
-
-  private:
-    int events_left = 0;
-};
-} // namespace
 
 TEST_CASE("CBOR")
 {
@@ -1875,19 +1801,40 @@ TEST_CASE("CBOR")
             CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<uint8_t>({0xA1, 0x7C, 0x01})), "[json.exception.parse_error.113] parse error at byte 2: syntax error while parsing CBOR string: expected length specification (0x60-0x7B) or indefinite string type (0x7F); last byte: 0x7C", json::parse_error&);
         }
 
-        SECTION("invalid UTF-8 in string (see #5529)")
+        SECTION("ill-formed UTF-8 in string (see #5529, #5651)")
         {
+            // RFC 8949 §3.1 leaves it up to the decoder whether to reject
+            // ill-formed UTF-8 in a text string; this library does not, and
+            // hands the original bytes back unchanged, matching the
+            // MessagePack reader and the behavior before #5185/#5531 (not in
+            // any release)
+
             // a two-character text string (major type 3) whose bytes are not
-            // valid UTF-8 (0xC0 0xAE is an overlong encoding of '.') must be
-            // rejected at decode time, matching every other kind of
-            // malformed binary input, rather than only failing later when
-            // the resulting value is dumped
-            json _;
-            CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<uint8_t>({0x62, 0xc0, 0xae})), "[json.exception.parse_error.113] parse error at byte 3: syntax error while parsing CBOR string: invalid string: ill-formed UTF-8 byte", json::parse_error&);
-            CHECK(json::from_cbor(std::vector<uint8_t>({0x62, 0xc0, 0xae}), true, false).is_discarded());
+            // valid UTF-8 (0xC0 0xAE is an overlong encoding of '.') round-trips
+            // byte for byte as a string value
+            const std::vector<uint8_t> ill_formed_value = {0x62, 0xc0, 0xae};
+            json j_value;
+            CHECK_NOTHROW(j_value = json::from_cbor(ill_formed_value));
+            REQUIRE(j_value.is_string());
+            CHECK(j_value.get_ref<const json::string_t&>() == std::string("\xc0\xae"));
+            // dump() still requires valid UTF-8 and throws for such a value,
+            // unless an error handler that replaces or ignores the bytes is
+            // passed
+            CHECK_THROWS_AS(j_value.dump(), json::type_error&);
+            // to_cbor() is strict as well, so the value cannot be written back
+            CHECK_THROWS_AS(json::to_cbor(j_value), json::type_error&);
+
+            // the same bytes as an object key round-trip as well
+            const std::vector<uint8_t> ill_formed_key = {0xa1, 0x62, 0xc0, 0xae, 0x01};
+            json j_key;
+            CHECK_NOTHROW(j_key = json::from_cbor(ill_formed_key));
+            REQUIRE(j_key.is_object());
+            CHECK(j_key.contains(std::string("\xc0\xae")));
+            CHECK_THROWS_AS(json::to_cbor(j_key), json::type_error&);
 
             // a CBOR byte string (major type 2) with the very same bytes is
             // NOT text and must still be accepted as-is
+            json _;
             CHECK_NOTHROW(_ = json::from_cbor(std::vector<uint8_t>({0x42, 0xc0, 0xae})));
             CHECK(_ == json::binary(std::vector<std::uint8_t>({0xc0, 0xae})));
 
@@ -1896,17 +1843,46 @@ TEST_CASE("CBOR")
             CHECK(json::from_cbor(json::to_cbor(j)) == j);
         }
 
-        SECTION("invalid UTF-8 in indefinite-length string")
+        SECTION("to_cbor rejects ill-formed UTF-8 (see #5651)")
+        {
+            // to_cbor() must reject the same ill-formed strings from_cbor()
+            // rejects, so a value it accepts can always be read back
+            CHECK_THROWS_WITH_AS(json::to_cbor(json("\xFF")), "[json.exception.type_error.316] invalid UTF-8 byte at index 0: 0xFF", json::type_error&);
+            // a truncated multi-byte sequence
+            CHECK_THROWS_WITH_AS(json::to_cbor(json("\xC3")), "[json.exception.type_error.316] invalid UTF-8 byte at index 0: 0xC3", json::type_error&);
+            // an encoded surrogate half (U+D800)
+            CHECK_THROWS_WITH_AS(json::to_cbor(json("\xED\xA0\x80")), "[json.exception.type_error.316] invalid UTF-8 byte at index 0: 0xED", json::type_error&);
+            // an overlong encoding of '.'
+            CHECK_THROWS_WITH_AS(json::to_cbor(json("\xC0\xAF")), "[json.exception.type_error.316] invalid UTF-8 byte at index 0: 0xC0", json::type_error&);
+
+            // an object key with ill-formed UTF-8 is rejected the same way
+            CHECK_THROWS_WITH_AS(json::to_cbor(json{{"\xFF", 1}}), "[json.exception.type_error.316] invalid UTF-8 byte at index 0: 0xFF", json::type_error&);
+
+            // binary values are not text and are unaffected
+            CHECK_NOTHROW(json::to_cbor(json::binary(std::vector<std::uint8_t>({0xFF}))));
+        }
+
+        SECTION("ill-formed UTF-8 in indefinite-length string")
         {
             json _;
 
-            // every chunk must be valid UTF-8 on its own (RFC 8949, Section
-            // 3.2.3), so a code point split across two chunks is rejected
-            CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<uint8_t>({0x7f, 0x61, 0xc3, 0x61, 0xa9, 0xff})), "[json.exception.parse_error.113] parse error at byte 3: syntax error while parsing CBOR string: invalid string: ill-formed UTF-8 byte", json::parse_error&);
-            CHECK(json::from_cbor(std::vector<uint8_t>({0x7f, 0x61, 0xc3, 0x61, 0xa9, 0xff}), true, false).is_discarded());
+            // the chunks are concatenated as is, without checking that each
+            // chunk is valid UTF-8 on its own (RFC 8949, Section 3.2.3), so
+            // a code point split across two chunks yields a valid string
+            CHECK_NOTHROW(_ = json::from_cbor(std::vector<uint8_t>({0x7f, 0x61, 0xc3, 0x61, 0xa9, 0xff})));
+            CHECK(_ == "\xc3\xa9");
+            CHECK(_.dump() == "\"\xc3\xa9\"");
 
-            // an ill-formed later chunk is rejected after valid ones
-            CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<uint8_t>({0x7f, 0x62, 0xc3, 0xa9, 0x62, 0xc0, 0xae, 0xff})), "[json.exception.parse_error.113] parse error at byte 7: syntax error while parsing CBOR string: invalid string: ill-formed UTF-8 byte", json::parse_error&);
+            // a truncated code point is kept as is
+            CHECK_NOTHROW(_ = json::from_cbor(std::vector<uint8_t>({0x7f, 0x61, 0xc3, 0xff})));
+            CHECK(_ == "\xc3");
+            CHECK_THROWS_AS(_.dump(), json::type_error&);
+            CHECK_THROWS_AS(json::to_cbor(_), json::type_error&);
+
+            // an ill-formed later chunk is kept after valid ones
+            CHECK_NOTHROW(_ = json::from_cbor(std::vector<uint8_t>({0x7f, 0x62, 0xc3, 0xa9, 0x62, 0xc0, 0xae, 0xff})));
+            CHECK(_ == "\xc3\xa9\xc0\xae");
+            CHECK_THROWS_AS(_.dump(), json::type_error&);
 
             // valid multi-byte chunks are accepted
             CHECK(json::from_cbor(std::vector<uint8_t>({0x7f, 0x62, 0xc3, 0xa9, 0x62, 0xc3, 0xb6, 0xff})) == "\xc3\xa9\xc3\xb6");
@@ -1914,9 +1890,6 @@ TEST_CASE("CBOR")
 
         SECTION("many chunks in indefinite-length string")
         {
-            // only the newly read chunk is validated, not the whole string
-            // collected so far; validating the latter made this input take
-            // quadratic time (about ten seconds for 100000 chunks)
             constexpr std::size_t chunks = 100000;
             std::vector<uint8_t> v{0x7f};
             for (std::size_t i = 0; i < chunks; ++i)
@@ -2415,6 +2388,39 @@ TEST_CASE("issue #5405 - array reserve for definite-length CBOR arrays")
     }
 }
 
+TEST_CASE("CBOR round-trip invariants")
+{
+    // This checks what the parse_cbor_fuzzer driver checks (see
+    // tests/src/fuzzer-parse_cbor.cpp), so that a regression shows up in CI
+    // rather than as an OSS-Fuzz report: anything from_cbor() returns (j1)
+    // can be serialized, parsed back (j2), and serialized again to reproduce
+    // the exact bytes.
+    for (const auto& j0 : utils::round_trip_corpus::values())
+    {
+        json j1;
+        try
+        {
+            // turn the corpus value into a value as from_cbor() returns it
+            j1 = json::from_cbor(json::to_cbor(j0));
+        }
+        catch (const json::exception&)
+        {
+            // not every corpus value survives a CBOR round trip (e.g., a
+            // binary subtype is written with a tag the default tag handler
+            // then rejects); the fuzzer driver only ever sees values
+            // from_cbor() actually produced, so skip those here, too
+            continue;
+        }
+
+        INFO("j1 = " << j1.dump());
+        const std::vector<std::uint8_t> vec = json::to_cbor(j1);
+        json j2;
+        // anything the library writes must be parsable by the library
+        REQUIRE_NOTHROW(j2 = json::from_cbor(vec));
+        CHECK(json::to_cbor(j2) == vec);
+    }
+}
+
 TEST_CASE("CBOR roundtrips" * doctest::skip())
 {
     SECTION("input from flynn")
@@ -2774,33 +2780,21 @@ TEST_CASE("examples from RFC 8949 Appendix A")
         CHECK(json::to_cbor(json::parse("1.1")) == std::vector<uint8_t>({0xfb, 0x3f, 0xf1, 0x99, 0x99, 0x99, 0x99, 0x99, 0x9a}));
         CHECK(json::parse("1.1") == json::from_cbor(std::vector<uint8_t>({0xfb, 0x3f, 0xf1, 0x99, 0x99, 0x99, 0x99, 0x99, 0x9a})));
 
-        // half-precision float
-        //CHECK(json::to_cbor(json::parse("1.5")) == std::vector<uint8_t>({0xf9, 0x3e, 0x00}));
+        // the writer never emits half-precision floats, so these can only be decoded, not encoded
         CHECK(json::parse("1.5") == json::from_cbor(std::vector<uint8_t>({0xf9, 0x3e, 0x00})));
-
-        // half-precision float
-        //CHECK(json::to_cbor(json::parse("65504.0")) == std::vector<uint8_t>({0xf9, 0x7b, 0xff}));
         CHECK(json::parse("65504.0") == json::from_cbor(std::vector<uint8_t>({0xf9, 0x7b, 0xff})));
 
-        //CHECK(json::to_cbor(json::parse("100000.0")) == std::vector<uint8_t>({0xfa, 0x47, 0xc3, 0x50, 0x00}));
+        CHECK(json::to_cbor(json::parse("100000.0")) == std::vector<uint8_t>({0xfa, 0x47, 0xc3, 0x50, 0x00}));
         CHECK(json::parse("100000.0") == json::from_cbor(std::vector<uint8_t>({0xfa, 0x47, 0xc3, 0x50, 0x00})));
 
-        //CHECK(json::to_cbor(json::parse("3.4028234663852886e+38")) == std::vector<uint8_t>({0xfa, 0x7f, 0x7f, 0xff, 0xff}));
+        CHECK(json::to_cbor(json::parse("3.4028234663852886e+38")) == std::vector<uint8_t>({0xfa, 0x7f, 0x7f, 0xff, 0xff}));
         CHECK(json::parse("3.4028234663852886e+38") == json::from_cbor(std::vector<uint8_t>({0xfa, 0x7f, 0x7f, 0xff, 0xff})));
 
         CHECK(json::to_cbor(json::parse("1.0e+300")) == std::vector<uint8_t>({0xfb, 0x7e, 0x37, 0xe4, 0x3c, 0x88, 0x00, 0x75, 0x9c}));
         CHECK(json::parse("1.0e+300") == json::from_cbor(std::vector<uint8_t>({0xfb, 0x7e, 0x37, 0xe4, 0x3c, 0x88, 0x00, 0x75, 0x9c})));
 
-        // half-precision float
-        //CHECK(json::to_cbor(json::parse("5.960464477539063e-8")) == std::vector<uint8_t>({0xf9, 0x00, 0x01}));
-        CHECK(json::parse("-4.0") == json::from_cbor(std::vector<uint8_t>({0xf9, 0xc4, 0x00})));
-
-        // half-precision float
-        //CHECK(json::to_cbor(json::parse("0.00006103515625")) == std::vector<uint8_t>({0xf9, 0x04, 0x00}));
-        CHECK(json::parse("-4.0") == json::from_cbor(std::vector<uint8_t>({0xf9, 0xc4, 0x00})));
-
-        // half-precision float
-        //CHECK(json::to_cbor(json::parse("-4.0")) == std::vector<uint8_t>({0xf9, 0xc4, 0x00}));
+        CHECK(json::parse("5.960464477539063e-8") == json::from_cbor(std::vector<uint8_t>({0xf9, 0x00, 0x01})));
+        CHECK(json::parse("0.00006103515625") == json::from_cbor(std::vector<uint8_t>({0xf9, 0x04, 0x00})));
         CHECK(json::parse("-4.0") == json::from_cbor(std::vector<uint8_t>({0xf9, 0xc4, 0x00})));
 
         CHECK(json::to_cbor(json::parse("-4.1")) == std::vector<uint8_t>({0xfb, 0xc0, 0x10, 0x66, 0x66, 0x66, 0x66, 0x66, 0x66}));
@@ -2931,7 +2925,7 @@ TEST_CASE("Tagged values")
         0xD5, 0xD6, 0xD7
     })
         {
-            CAPTURE(b);
+            CAPTURE(b)
 
             // add tag to value
             auto v_tagged = v;
@@ -3271,7 +3265,7 @@ TEST_CASE("CBOR large strings and binaries (chunked reader)")
                 std::size_t{4097}, std::size_t{8192}, std::size_t{100000}
             })
     {
-        CAPTURE(len);
+        CAPTURE(len)
 
         // text string
         const json j_string = std::string(len, 'x');

tests/src/unit-class_lexer.cpp

@@ -272,7 +272,7 @@ TEST_CASE("lexer number fast path")
             std::stringstream ss(doc);
             const json b = json::parse(ss);
 
-            CAPTURE(n);
+            CAPTURE(n)
             CHECK(a == b);
             CHECK(a.dump() == b.dump());
             CHECK(a[0].type() == b[0].type());
@@ -310,7 +310,7 @@ TEST_CASE("lexer number fast path")
 
         for (const auto& n : numbers)
         {
-            CAPTURE(n);
+            CAPTURE(n)
             const std::string doc = "[" + n + "]";
 
             const json a = json::parse(doc);   // contiguous fast path
@@ -347,7 +347,7 @@ TEST_CASE("lexer number fast path")
                 {"-", "1.", "1e", "1e+", "1.2e", "01", "-01", "1..2", "1.2.3"
                 })
         {
-            CAPTURE(bad);
+            CAPTURE(bad)
             // the contiguous fast path must decline and let the byte path report
             const std::string doc = std::string("[") + bad + "]";
             CHECK_FALSE(json::accept(doc));
@@ -415,7 +415,7 @@ TEST_CASE("lexer number fast path")
 
         // 7 + 49 + 343 + 2401 tokens
         CHECK(tokens.size() == 2401);
-        CAPTURE(mismatches);
+        CAPTURE(mismatches)
         CHECK(mismatches.empty());
     }
 
@@ -459,7 +459,7 @@ TEST_CASE("lexer number fast path")
                  "[1 \n2]", "[\n1\n2]", "1\n2", "[01\r\n]", "[1e\n]", "[-\n]"
                 })
         {
-            CAPTURE(bad);
+            CAPTURE(bad)
             const std::string doc = bad;
             const std::string contiguous_what = contiguous_error(doc);
 
@@ -576,7 +576,7 @@ TEST_CASE("lexer string fast path")
 
         // 13 + 169 + 2197 tokens, each at two offsets
         CHECK(tokens.size() == 2197);
-        CAPTURE(mismatches);
+        CAPTURE(mismatches)
         CHECK(mismatches.empty());
     }
 
@@ -604,7 +604,7 @@ TEST_CASE("lexer string fast path")
                 }
             }
         }
-        CAPTURE(mismatches);
+        CAPTURE(mismatches)
         CHECK(mismatches.empty());
     }
 #endif
@@ -649,10 +649,10 @@ TEST_CASE("lexer string fast path")
 
         for (const auto& test_case : cases)
         {
-            CAPTURE(test_case.description);
+            CAPTURE(test_case.description)
             for (const std::size_t offset : offsets)
             {
-                CAPTURE(offset);
+                CAPTURE(offset)
                 const std::string doc = "[\"" + std::string(offset, 'a') + test_case.sequence + "\"]";
                 CHECK(json::accept(doc) == test_case.valid);
 #if !defined(JSON_NOEXCEPTION)
@@ -1236,7 +1236,7 @@ TEST_CASE("Eisel-Lemire float conversion")
 
         for (const auto& c : known)
         {
-            CAPTURE(c.first);
+            CAPTURE(c.first)
             double out = 0;
             if (eisel_lemire(c.first, out))
             {
@@ -1277,7 +1277,7 @@ TEST_CASE("Eisel-Lemire float conversion")
             std::array<char, 64> buffer{};
             const char* end = nlohmann::detail::to_chars(buffer.data(), buffer.data() + buffer.size(), d);
             const std::string token(buffer.data(), static_cast<std::size_t>(end - buffer.data()));
-            CAPTURE(token);
+            CAPTURE(token)
             double out = 0;
             REQUIRE(eisel_lemire(token, out));
             CHECK(bits_of(out) == b);
@@ -1289,7 +1289,7 @@ TEST_CASE("Eisel-Lemire float conversion")
             const std::size_t dot = longer.find('.');
             const std::string extra = dot == std::string::npos ? ".000000000000000000001" : "000000000000000000001";
             longer.insert(e == std::string::npos ? longer.size() : e, extra);
-            CAPTURE(longer);
+            CAPTURE(longer)
             if (eisel_lemire(longer, out))
             {
                 CHECK(bits_of(out) == b);

tests/src/unit-class_parser.cpp

@@ -2561,7 +2561,7 @@ TEST_CASE("last-read diagnostics are identical across input adapters")
 
     for (const auto& s : inputs)
     {
-        CAPTURE(s);
+        CAPTURE(s)
 
         // reference: contiguous std::string -> seekable (lazy) path
         const std::string reference = parse_error_message(s);
@@ -2645,7 +2645,7 @@ TEST_CASE("diagnostic positions: value lifetime, input adapters, and SAX")
 
         SECTION("move constructor resets the moved-from value to npos")
         {
-            // basic_json(basic_json&&) (json.hpp, around line 1265) copies
+            // basic_json(basic_json&&) (json.hpp, around line 1951) copies
             // other's start_position/end_position into *this and then resets
             // other's to npos (see the cppcheck-suppress[accessForwarded]
             // annotation there, which flags this reset as worth a second

tests/src/unit-comparison.cpp

@@ -857,7 +857,7 @@ TEST_CASE("equality of objects whose entries have no fixed order")
 
     for (const std::size_t depth : std::vector<std::size_t> {0, 200})
     {
-        CAPTURE(depth);
+        CAPTURE(depth)
 
         const unordered_json descending = nest(make_unordered_object(true), depth);
         const unordered_json ascending = nest(make_unordered_object(false), depth);
@@ -909,7 +909,7 @@ TEST_CASE("equality of an object whose comparator treats different keys as equiv
 
     for (const std::size_t depth : std::vector<std::size_t> {0, 127, 128, 200})
     {
-        CAPTURE(depth);
+        CAPTURE(depth)
 
         const ci_json x = nest(a, depth);
         const ci_json y = nest(b, depth);
@@ -935,7 +935,7 @@ TEST_CASE("containers are compared element by element")
 
     for (const std::size_t depth : std::vector<std::size_t> {0, 200})
     {
-        CAPTURE(depth);
+        CAPTURE(depth)
 
         // objects with different keys
         {

tests/src/unit-constructor2.cpp

@@ -85,7 +85,7 @@ TEST_CASE("other constructors and destructor")
         CHECK(j.type() == json::value_t::object);
         const json k(std::move(j));
         CHECK(k.type() == json::value_t::object);
-        CHECK(j.type() == json::value_t::null); // NOLINT: access after move is OK here
+        CHECK(j.type() == json::value_t::null); // NOLINT(bugprone-use-after-move,hicpp-invalid-access-moved) access after move is OK here
     }
 
     SECTION("copy assignment")

tests/src/unit-conversions.cpp

@@ -1380,21 +1380,22 @@ TEST_CASE("value conversion")
 
             SECTION("std::map")
             {
-                j1.get<std::map<std::string, int>>();
-                j2.get<std::map<std::string, unsigned int>>();
-                j3.get<std::map<std::string, double>>();
-                j4.get<std::map<std::string, bool>>();
-                j5.get<std::map<std::string, std::string>>();
+                CHECK(j1.get<std::map<std::string, int>>() == (std::map<std::string, int> {{"one", 1}, {"two", 2}, {"three", 3}}));
+                CHECK(j2.get<std::map<std::string, unsigned int>>() == (std::map<std::string, unsigned int> {{"one", 1u}, {"two", 2u}, {"three", 3u}}));
+                CHECK(j3.get<std::map<std::string, double>>() == (std::map<std::string, double> {{"one", 1.1}, {"two", 2.2}, {"three", 3.3}}));
+                CHECK(j4.get<std::map<std::string, bool>>() == (std::map<std::string, bool> {{"one", true}, {"two", false}, {"three", true}}));
+                CHECK(j5.get<std::map<std::string, std::string>>() == (std::map<std::string, std::string> {{"one", "eins"}, {"two", "zwei"}, {"three", "drei"}}));
             }
 
             SECTION("std::unordered_map")
             {
-                j1.get<std::unordered_map<std::string, int>>();
-                j2.get<std::unordered_map<std::string, unsigned int>>();
-                j3.get<std::unordered_map<std::string, double>>();
-                j4.get<std::unordered_map<std::string, bool>>();
-                j5.get<std::unordered_map<std::string, std::string>>();
-                // CHECK(m5["one"] == "eins");
+                CHECK(j1.get<std::unordered_map<std::string, int>>() == (std::unordered_map<std::string, int> {{"one", 1}, {"two", 2}, {"three", 3}}));
+                CHECK(j2.get<std::unordered_map<std::string, unsigned int>>() == (std::unordered_map<std::string, unsigned int> {{"one", 1u}, {"two", 2u}, {"three", 3u}}));
+                CHECK(j3.get<std::unordered_map<std::string, double>>() == (std::unordered_map<std::string, double> {{"one", 1.1}, {"two", 2.2}, {"three", 3.3}}));
+                CHECK(j4.get<std::unordered_map<std::string, bool>>() == (std::unordered_map<std::string, bool> {{"one", true}, {"two", false}, {"three", true}}));
+                const auto m5 = j5.get<std::unordered_map<std::string, std::string>>();
+                CHECK(m5 == (std::unordered_map<std::string, std::string> {{"one", "eins"}, {"two", "zwei"}, {"three", "drei"}}));
+                CHECK(m5.at("one") == "eins");
             }
 
             SECTION("reserve is called on containers that support it (#5406)")
@@ -1430,22 +1431,24 @@ TEST_CASE("value conversion")
 
             SECTION("std::multimap")
             {
-                j1.get<std::multimap<std::string, int>>();
-                j2.get<std::multimap<std::string, unsigned int>>();
-                j3.get<std::multimap<std::string, double>>();
-                j4.get<std::multimap<std::string, bool>>();
-                j5.get<std::multimap<std::string, std::string>>();
-                // CHECK(m5["one"] == "eins");
+                CHECK(j1.get<std::multimap<std::string, int>>() == (std::multimap<std::string, int> {{"one", 1}, {"two", 2}, {"three", 3}}));
+                CHECK(j2.get<std::multimap<std::string, unsigned int>>() == (std::multimap<std::string, unsigned int> {{"one", 1u}, {"two", 2u}, {"three", 3u}}));
+                CHECK(j3.get<std::multimap<std::string, double>>() == (std::multimap<std::string, double> {{"one", 1.1}, {"two", 2.2}, {"three", 3.3}}));
+                CHECK(j4.get<std::multimap<std::string, bool>>() == (std::multimap<std::string, bool> {{"one", true}, {"two", false}, {"three", true}}));
+                const auto m5 = j5.get<std::multimap<std::string, std::string>>();
+                CHECK(m5 == (std::multimap<std::string, std::string> {{"one", "eins"}, {"two", "zwei"}, {"three", "drei"}}));
+                CHECK(m5.find("one")->second == "eins");
             }
 
             SECTION("std::unordered_multimap")
             {
-                j1.get<std::unordered_multimap<std::string, int>>();
-                j2.get<std::unordered_multimap<std::string, unsigned int>>();
-                j3.get<std::unordered_multimap<std::string, double>>();
-                j4.get<std::unordered_multimap<std::string, bool>>();
-                j5.get<std::unordered_multimap<std::string, std::string>>();
-                // CHECK(m5["one"] == "eins");
+                CHECK(j1.get<std::unordered_multimap<std::string, int>>() == (std::unordered_multimap<std::string, int> {{"one", 1}, {"two", 2}, {"three", 3}}));
+                CHECK(j2.get<std::unordered_multimap<std::string, unsigned int>>() == (std::unordered_multimap<std::string, unsigned int> {{"one", 1u}, {"two", 2u}, {"three", 3u}}));
+                CHECK(j3.get<std::unordered_multimap<std::string, double>>() == (std::unordered_multimap<std::string, double> {{"one", 1.1}, {"two", 2.2}, {"three", 3.3}}));
+                CHECK(j4.get<std::unordered_multimap<std::string, bool>>() == (std::unordered_multimap<std::string, bool> {{"one", true}, {"two", false}, {"three", true}}));
+                const auto m5 = j5.get<std::unordered_multimap<std::string, std::string>>();
+                CHECK(m5 == (std::unordered_multimap<std::string, std::string> {{"one", "eins"}, {"two", "zwei"}, {"three", "drei"}}));
+                CHECK(m5.find("one")->second == "eins");
             }
 
             SECTION("exception in case of a non-object type")
@@ -1466,29 +1469,30 @@ TEST_CASE("value conversion")
 
             SECTION("std::list")
             {
-                j1.get<std::list<int>>();
-                j2.get<std::list<unsigned int>>();
-                j3.get<std::list<double>>();
-                j4.get<std::list<bool>>();
-                j5.get<std::list<std::string>>();
+                CHECK(j1.get<std::list<int>>() == (std::list<int> {1, 2, 3, 4}));
+                CHECK(j2.get<std::list<unsigned int>>() == (std::list<unsigned int> {1u, 2u, 3u, 4u}));
+                CHECK(j3.get<std::list<double>>() == (std::list<double> {1.2, 2.3, 3.4, 4.5}));
+                CHECK(j4.get<std::list<bool>>() == (std::list<bool> {true, false, true}));
+                CHECK(j5.get<std::list<std::string>>() == (std::list<std::string> {"one", "two", "three"}));
             }
 
             SECTION("std::forward_list")
             {
-                j1.get<std::forward_list<int>>();
-                j2.get<std::forward_list<unsigned int>>();
-                j3.get<std::forward_list<double>>();
-                j4.get<std::forward_list<bool>>();
-                j5.get<std::forward_list<std::string>>();
+                CHECK(j1.get<std::forward_list<int>>() == (std::forward_list<int> {1, 2, 3, 4}));
+                CHECK(j2.get<std::forward_list<unsigned int>>() == (std::forward_list<unsigned int> {1u, 2u, 3u, 4u}));
+                CHECK(j3.get<std::forward_list<double>>() == (std::forward_list<double> {1.2, 2.3, 3.4, 4.5}));
+                CHECK(j4.get<std::forward_list<bool>>() == (std::forward_list<bool> {true, false, true}));
+                CHECK(j5.get<std::forward_list<std::string>>() == (std::forward_list<std::string> {"one", "two", "three"}));
             }
 
             SECTION("std::array")
             {
-                j1.get<std::array<int, 4>>();
-                j2.get<std::array<unsigned int, 3>>();
-                j3.get<std::array<double, 4>>();
-                j4.get<std::array<bool, 3>>();
-                j5.get<std::array<std::string, 3>>();
+                CHECK(j1.get<std::array<int, 4>>() == (std::array<int, 4> {{1, 2, 3, 4}}));
+                // only the first 3 elements of j2 are converted, since the target array is smaller
+                CHECK(j2.get<std::array<unsigned int, 3>>() == (std::array<unsigned int, 3> {{1u, 2u, 3u}}));
+                CHECK(j3.get<std::array<double, 4>>() == (std::array<double, 4> {{1.2, 2.3, 3.4, 4.5}}));
+                CHECK(j4.get<std::array<bool, 3>>() == (std::array<bool, 3> {{true, false, true}}));
+                CHECK(j5.get<std::array<std::string, 3>>() == (std::array<std::string, 3> {{"one", "two", "three"}}));
 
                 SECTION("std::array is larger than JSON")
                 {
@@ -1508,47 +1512,53 @@ TEST_CASE("value conversion")
 
             SECTION("std::valarray")
             {
-                j1.get<std::valarray<int>>();
-                j2.get<std::valarray<unsigned int>>();
-                j3.get<std::valarray<double>>();
-                j4.get<std::valarray<bool>>();
-                j5.get<std::valarray<std::string>>();
+                // valarray has no operator== that returns bool, so compare via a vector copy
+                const auto v1 = j1.get<std::valarray<int>>();
+                CHECK((std::vector<int>(std::begin(v1), std::end(v1)) == std::vector<int> {1, 2, 3, 4}));
+                const auto v2 = j2.get<std::valarray<unsigned int>>();
+                CHECK((std::vector<unsigned int>(std::begin(v2), std::end(v2)) == std::vector<unsigned int> {1u, 2u, 3u, 4u}));
+                const auto v3 = j3.get<std::valarray<double>>();
+                CHECK((std::vector<double>(std::begin(v3), std::end(v3)) == std::vector<double> {1.2, 2.3, 3.4, 4.5}));
+                const auto v4 = j4.get<std::valarray<bool>>();
+                CHECK((std::vector<bool>(std::begin(v4), std::end(v4)) == std::vector<bool> {true, false, true}));
+                const auto v5 = j5.get<std::valarray<std::string>>();
+                CHECK((std::vector<std::string>(std::begin(v5), std::end(v5)) == std::vector<std::string> {"one", "two", "three"}));
             }
 
             SECTION("std::vector")
             {
-                j1.get<std::vector<int>>();
-                j2.get<std::vector<unsigned int>>();
-                j3.get<std::vector<double>>();
-                j4.get<std::vector<bool>>();
-                j5.get<std::vector<std::string>>();
+                CHECK(j1.get<std::vector<int>>() == (std::vector<int> {1, 2, 3, 4}));
+                CHECK(j2.get<std::vector<unsigned int>>() == (std::vector<unsigned int> {1u, 2u, 3u, 4u}));
+                CHECK(j3.get<std::vector<double>>() == (std::vector<double> {1.2, 2.3, 3.4, 4.5}));
+                CHECK(j4.get<std::vector<bool>>() == (std::vector<bool> {true, false, true}));
+                CHECK(j5.get<std::vector<std::string>>() == (std::vector<std::string> {"one", "two", "three"}));
             }
 
             SECTION("std::deque")
             {
-                j1.get<std::deque<int>>();
-                j2.get<std::deque<unsigned int>>();
-                j2.get<std::deque<double>>();
-                j4.get<std::deque<bool>>();
-                j5.get<std::deque<std::string>>();
+                CHECK(j1.get<std::deque<int>>() == (std::deque<int> {1, 2, 3, 4}));
+                CHECK(j2.get<std::deque<unsigned int>>() == (std::deque<unsigned int> {1u, 2u, 3u, 4u}));
+                CHECK(j3.get<std::deque<double>>() == (std::deque<double> {1.2, 2.3, 3.4, 4.5}));
+                CHECK(j4.get<std::deque<bool>>() == (std::deque<bool> {true, false, true}));
+                CHECK(j5.get<std::deque<std::string>>() == (std::deque<std::string> {"one", "two", "three"}));
             }
 
             SECTION("std::set")
             {
-                j1.get<std::set<int>>();
-                j2.get<std::set<unsigned int>>();
-                j3.get<std::set<double>>();
-                j4.get<std::set<bool>>();
-                j5.get<std::set<std::string>>();
+                CHECK(j1.get<std::set<int>>() == (std::set<int> {1, 2, 3, 4}));
+                CHECK(j2.get<std::set<unsigned int>>() == (std::set<unsigned int> {1u, 2u, 3u, 4u}));
+                CHECK(j3.get<std::set<double>>() == (std::set<double> {1.2, 2.3, 3.4, 4.5}));
+                CHECK(j4.get<std::set<bool>>() == (std::set<bool> {true, false, true}));
+                CHECK(j5.get<std::set<std::string>>() == (std::set<std::string> {"one", "two", "three"}));
             }
 
             SECTION("std::unordered_set")
             {
-                j1.get<std::unordered_set<int>>();
-                j2.get<std::unordered_set<unsigned int>>();
-                j3.get<std::unordered_set<double>>();
-                j4.get<std::unordered_set<bool>>();
-                j5.get<std::unordered_set<std::string>>();
+                CHECK(j1.get<std::unordered_set<int>>() == (std::unordered_set<int> {1, 2, 3, 4}));
+                CHECK(j2.get<std::unordered_set<unsigned int>>() == (std::unordered_set<unsigned int> {1u, 2u, 3u, 4u}));
+                CHECK(j3.get<std::unordered_set<double>>() == (std::unordered_set<double> {1.2, 2.3, 3.4, 4.5}));
+                CHECK(j4.get<std::unordered_set<bool>>() == (std::unordered_set<bool> {true, false, true}));
+                CHECK(j5.get<std::unordered_set<std::string>>() == (std::unordered_set<std::string> {"one", "two", "three"}));
             }
 
             SECTION("std::map (array of pairs)")
@@ -1630,7 +1640,7 @@ TEST_CASE("value conversion")
 
 enum class cards {kreuz, pik, herz, karo};
 
-// NOLINTNEXTLINE(misc-use-internal-linkage,misc-const-correctness,cppcoreguidelines-avoid-c-arrays,hicpp-avoid-c-arrays,modernize-avoid-c-arrays) - false positive
+// NOLINTNEXTLINE(misc-use-internal-linkage,misc-const-correctness) - false positive
 NLOHMANN_JSON_SERIALIZE_ENUM(cards,
 {
     {cards::kreuz, "kreuz"},
@@ -1648,7 +1658,7 @@ enum TaskState // NOLINT(cert-int09-c,readability-enum-initial-value,cppcoreguid
     TS_INVALID = -1,
 };
 
-// NOLINTNEXTLINE(misc-const-correctness,misc-use-internal-linkage,cppcoreguidelines-avoid-c-arrays,hicpp-avoid-c-arrays,modernize-avoid-c-arrays) - false positive
+// NOLINTNEXTLINE(misc-const-correctness,misc-use-internal-linkage) - false positive
 NLOHMANN_JSON_SERIALIZE_ENUM(TaskState,
 {
     {TS_INVALID, nullptr},
@@ -1698,7 +1708,7 @@ TEST_CASE("JSON to enum mapping")
 
 enum class strict_cards {kreuz, pik, herz, karo, andere}; // andere not included in mapping
 
-// NOLINTNEXTLINE(misc-use-internal-linkage,misc-const-correctness,cppcoreguidelines-avoid-c-arrays,hicpp-avoid-c-arrays,modernize-avoid-c-arrays) - false positive
+// NOLINTNEXTLINE(misc-use-internal-linkage,misc-const-correctness) - false positive
 NLOHMANN_JSON_SERIALIZE_ENUM_STRICT(strict_cards,
 {
     {strict_cards::kreuz, "kreuz"},
@@ -1717,7 +1727,7 @@ enum StrictTaskState // NOLINT(cert-int09-c,readability-enum-initial-value,cppco
     STRICT_TS_INVALID = -1,
 };
 
-// NOLINTNEXTLINE(misc-const-correctness,misc-use-internal-linkage,cppcoreguidelines-avoid-c-arrays,hicpp-avoid-c-arrays,modernize-avoid-c-arrays) - false positive
+// NOLINTNEXTLINE(misc-const-correctness,misc-use-internal-linkage) - false positive
 NLOHMANN_JSON_SERIALIZE_ENUM_STRICT(StrictTaskState,
 {
     {STRICT_TS_INVALID, nullptr},

tests/src/unit-deserialization.cpp

@@ -28,11 +28,6 @@ using nlohmann::json;
 #include <string>
 #include <valarray>
 
-#if defined(_WIN32)
-    #define NOMINMAX
-    #include <windows.h> // for GetACP()
-#endif
-
 namespace
 {
 struct SaxEventLogger : public nlohmann::json_sax<json>
@@ -228,24 +223,6 @@ class proxy_iterator
     iterator* m_it = nullptr;
 };
 
-// JSON_HAS_CPP_20
-#if defined(__cpp_char8_t)
-bool check_utf8()
-{
-#if defined(_WIN32)
-    // Runtime check of the active ANSI code page
-    // 65001 == UTF-8
-    return GetACP() == 65001;
-#elif defined(__ICC) || defined(__INTEL_COMPILER)
-    // classic Intel ICC does not encode narrow string literals containing
-    // non-ASCII source characters as UTF-8, so comparing a decoded u8 literal
-    // against a narrow string literal containing the same characters fails
-    return false;
-#else
-    return true;
-#endif
-}
-#endif
 } // namespace
 
 TEST_CASE("deserialization")
@@ -1328,14 +1305,15 @@ TEST_CASE("deserialization")
         CHECK(j1["key"] == "value");
         CHECK(j1["num"] == 42);
 
-        // UTF-8 prefixed literal (C++20 and later);
-        // MSVC may not set /utf-8, so we need to check
-        if (check_utf8())
-        {
-            const auto j2 = u8R"({"emoji": "😀", "msg": "hello"})"_json;
-            CHECK(j2["emoji"] == "😀");
-            CHECK(j2["msg"] == "hello");
-        }
+        // UTF-8 prefixed literal (C++20 and later); the emoji is written as a
+        // \U escape rather than a raw multibyte character so this does not
+        // depend on the compiler's source-file encoding (e.g., MSVC without
+        // /utf-8, or classic ICC, which does not encode non-ASCII narrow
+        // string literals as UTF-8 - compare against a \x-escaped expectation
+        // for the same reason)
+        const auto j2 = u8"{\"emoji\": \"\U0001F600\", \"msg\": \"hello\"}"_json;
+        CHECK(j2["emoji"] == "\xF0\x9F\x98\x80");
+        CHECK(j2["msg"] == "hello");
 
         const auto j3 = u8R"({"key": "value", "num": 42})"_json;
         CHECK(j3["key"] == "value");

tests/src/unit-hash.cpp

@@ -191,7 +191,7 @@ TEST_CASE("hash of deeply nested values")
         // every depth on either side of where the iterative path takes over
         for (std::size_t depth = 0; depth <= (2 * nlohmann::detail::recursion_depth_limit()) + 10; ++depth)
         {
-            CAPTURE(depth);
+            CAPTURE(depth)
             const auto arrays = nested<json>(depth, false);
             const auto objects = nested<json>(depth, true);
             const auto ordered = nested<ordered_json>(depth, true);
@@ -212,7 +212,7 @@ TEST_CASE("hash of deeply nested values")
                     false, true
                 })
         {
-            CAPTURE(objects);
+            CAPTURE(objects)
             const auto text = nested_text(depth, objects);
             const auto a = json::parse(text);
             const auto b = json::parse(text);

tests/src/unit-iterators2.cpp

@@ -893,8 +893,6 @@ TEST_CASE("iterators 2")
             CHECK(std::ranges::input_range<items_type>);
         }
 
-        // libstdc++ algorithms don't work with Clang 15 (04/2022)
-#if !DOCTEST_CLANG || (DOCTEST_CLANG && defined(__GLIBCXX__))
         SECTION("algorithms")
         {
             SECTION("copy")
@@ -929,11 +927,7 @@ TEST_CASE("iterators 2")
                 CHECK(*it == 2);
             }
         }
-#endif
 
-        // libstdc++ views don't work with Clang 15 (04/2022)
-        // libc++ hides limited ranges implementation behind guard macro
-#if !(DOCTEST_CLANG && (defined(__GLIBCXX__) || defined(_LIBCPP_HAS_NO_INCOMPLETE_RANGES)))
         SECTION("views")
         {
             SECTION("reverse")
@@ -966,7 +960,6 @@ TEST_CASE("iterators 2")
                 CHECK(j_transformed == j_expected);
             }
         }
-#endif
     }
 #endif
 }

tests/src/unit-json_patch.cpp

@@ -15,8 +15,65 @@ using nlohmann::json;
 #endif
 
 #include <fstream>
+#include <string>
+#include <vector>
 #include "make_test_data_available.hpp"
 
+namespace
+{
+// alternating objects and arrays nested `depth` levels deep, with members that
+// depend on `variant` at some levels, so diffing two variants yields
+// operations on many levels: replacing the innermost value, adding, removing,
+// and (for ordered_json) reordering members, and changing array lengths
+template<typename BasicJsonType>
+BasicJsonType nested(const std::size_t depth, const int variant)
+{
+    BasicJsonType value = variant;
+    for (std::size_t i = 0; i < depth; ++i)
+    {
+        if (i % 2 == 0)
+        {
+            BasicJsonType object = BasicJsonType::object();
+            if ((i + static_cast<std::size_t>(variant)) % 7 == 0)
+            {
+                object["x"] = i;
+            }
+            if (variant == 2 && i % 11 == 0)
+            {
+                object["z"] = "z";
+            }
+            object["a"] = std::move(value);
+            if (variant == 1 && i % 5 == 0)
+            {
+                object["y"] = 1;
+            }
+            value = std::move(object);
+        }
+        else
+        {
+            BasicJsonType array = BasicJsonType::array({std::move(value)});
+            if ((i + static_cast<std::size_t>(variant)) % 3 == 0)
+            {
+                array.push_back(i);
+            }
+            value = std::move(array);
+        }
+    }
+    return value;
+}
+
+// a path of `depth` reference tokens, as nested() nests its values
+std::string nested_path(const std::size_t depth)
+{
+    std::string path;
+    for (std::size_t i = depth; i > 0; --i)
+    {
+        path += (i - 1) % 2 == 0 ? "/a" : "/0";
+    }
+    return path;
+}
+} // namespace
+
 TEST_CASE("JSON patch")
 {
     SECTION("examples from RFC 6902")
@@ -1752,6 +1809,102 @@ TEST_CASE("JSON patch - diff emits array removals in descending index order")
     }
 }
 
+TEST_CASE("JSON patch: diff of deeply nested values")
+{
+    SECTION("the diff reproduces the target at every depth")
+    {
+        // depths on either side of the nesting depth up to which diff()
+        // recurses (detail::recursion_depth_limit(), 128); not every depth up
+        // to 300, as the test would then time out under Valgrind
+        std::vector<std::size_t> depths;
+        for (std::size_t depth = 0; depth <= 16; ++depth)
+        {
+            depths.push_back(depth);
+        }
+        for (std::size_t depth = 120; depth <= 136; ++depth)
+        {
+            depths.push_back(depth);
+        }
+        depths.push_back(300);
+
+        for (const auto depth : depths)
+        {
+            CAPTURE(depth)
+            for (int from = 0; from < 3; ++from)
+            {
+                for (int to = 0; to < 3; ++to)
+                {
+                    CAPTURE(from)
+                    CAPTURE(to)
+                    const auto source = nested<json>(depth, from);
+                    const auto target = nested<json>(depth, to);
+                    const auto patch = json::diff(source, target);
+                    CHECK(source.patch(patch) == target);
+                    CHECK(patch.empty() == (from == to));
+
+                    const auto ordered_source = nested<nlohmann::ordered_json>(depth, from);
+                    const auto ordered_target = nested<nlohmann::ordered_json>(depth, to);
+                    CHECK(ordered_source.patch(nlohmann::ordered_json::diff(ordered_source, ordered_target)) == ordered_target);
+                }
+            }
+        }
+    }
+
+    SECTION("a difference only in the innermost value is one replace operation")
+    {
+        for (std::size_t depth = 0; depth <= 300; ++depth)
+        {
+            CAPTURE(depth)
+            json source = 1;
+            json target = 2;
+            for (std::size_t i = 0; i < depth; ++i)
+            {
+                source = i % 2 == 0 ? json::object({{"a", std::move(source)}}) : json::array({std::move(source)});
+                target = i % 2 == 0 ? json::object({{"a", std::move(target)}}) : json::array({std::move(target)});
+            }
+            CHECK(json::diff(source, target, "/root") == json::array({{{"op", "replace"}, {"path", "/root" + nested_path(depth)}, {"value", 2}}}));
+        }
+    }
+
+    SECTION("values nested too deeply for the call stack (#5393)")
+    {
+        // diff() used to recurse once per nesting level, and compared the
+        // values with operator== on every level. The values are only
+        // parsed and diffed, never copied or compared, since those recurse
+        // too.
+        const std::size_t depth = 100000;
+        for (const bool objects :
+                {
+                    false, true
+                })
+        {
+            CAPTURE(objects)
+            std::string source_text;
+            std::string target_text;
+            std::string equal_text;
+            std::string path;
+            for (std::size_t i = 0; i < depth; ++i)
+            {
+                source_text += objects ? "{\"a\":" : "[";
+                path += objects ? "/a" : "/0";
+            }
+            target_text = source_text + "2";
+            equal_text = source_text + "1";
+            source_text += "1";
+            const std::string closing(depth, objects ? '}' : ']');
+            const auto source = json::parse(source_text + closing);
+
+            const auto patch = json::diff(source, json::parse(target_text + closing));
+            REQUIRE(patch.size() == 1);
+            CHECK(patch[0]["op"] == "replace");
+            CHECK(patch[0]["path"] == path);
+            CHECK(patch[0]["value"] == 2);
+
+            CHECK(json::diff(source, json::parse(equal_text + closing)).empty());
+        }
+    }
+}
+
 TEST_CASE("JSON patch - diff() takes the fast path for non-reorderable object types (regression #5639)")
 {
     // #5465 added an order check to diff()'s object handling so a
@@ -1893,7 +2046,7 @@ TEST_CASE("JSON patch - every operation on ordered_json")
         };
         for (const auto& target : targets)
         {
-            CAPTURE(target.dump());
+            CAPTURE(target.dump())
             CHECK(source.patch(ordered_json::diff(source, target)) == target);
         }
     }

tests/src/unit-large_json.cpp

@@ -135,7 +135,7 @@ TEST_CASE("tests on deeply nested JSONs")
             // are known to meet cleanly - wherever the bound is set.
             for (std::size_t d = 1; d <= 300; ++d)
             {
-                CAPTURE(d);
+                CAPTURE(d)
 
                 const json array = json::parse(std::string(d, '[') + '0' + std::string(d, ']'));
                 const json array_copy(array); // NOLINT(performance-unnecessary-copy-initialization): the copy is what is tested
@@ -252,7 +252,7 @@ TEST_CASE("tests on deeply nested JSONs")
         {
             for (const auto& pattern : patterns)
             {
-                CAPTURE(pattern);
+                CAPTURE(pattern)
                 const std::string text = nested_text(depth, pattern);
                 const json j = json::parse(text);
 
@@ -265,7 +265,7 @@ TEST_CASE("tests on deeply nested JSONs")
         {
             for (const auto& pattern : patterns)
             {
-                CAPTURE(pattern);
+                CAPTURE(pattern)
                 const std::string text = nested_text(depth, pattern);
                 const nlohmann::ordered_json o = nlohmann::ordered_json::parse(text);
 
@@ -278,7 +278,7 @@ TEST_CASE("tests on deeply nested JSONs")
         {
             for (const auto& pattern : patterns)
             {
-                CAPTURE(pattern);
+                CAPTURE(pattern)
                 const std::string text = nested_text(depth, pattern);
                 const json j = json::parse(text);
 
@@ -290,10 +290,10 @@ TEST_CASE("tests on deeply nested JSONs")
         {
             for (std::size_t d = 1; d <= 300; ++d)
             {
-                CAPTURE(d);
+                CAPTURE(d)
                 for (const auto& pattern : patterns)
                 {
-                    CAPTURE(pattern);
+                    CAPTURE(pattern)
                     const std::string text = nested_text(d, pattern);
                     const json j = json::parse(text);
 

tests/src/unit-locale-cpp.cpp

@@ -14,7 +14,10 @@ using nlohmann::json;
 
 #include <array>
 #include <clocale>
+#include <limits>
 #include <map>
+#include <ostream>
+#include <streambuf>
 #include <string>
 #include <utility>
 #include <vector>
@@ -286,8 +289,8 @@ TEST_CASE("locale changes between lexer construction and number conversion (#519
 
     for (const auto& transition : transitions)
     {
-        CAPTURE(transition.first);
-        CAPTURE(transition.second);
+        CAPTURE(transition.first)
+        CAPTURE(transition.second)
 
         if (std::setlocale(LC_NUMERIC, transition.first) == nullptr)
         {
@@ -365,7 +368,7 @@ TEST_CASE("locale with a multi-byte decimal point")
         {
             continue;
         }
-        CAPTURE(name);
+        CAPTURE(name)
         tested = true;
 
         // too many significant digits for Clinger's fast path, and an underflow
@@ -385,3 +388,92 @@ TEST_CASE("locale with a multi-byte decimal point")
 
     CHECK(std::setlocale(LC_NUMERIC, "C") != nullptr);
 }
+
+namespace
+{
+// a streambuf that switches LC_NUMERIC the first time anything is written to
+// it, so a dump() in progress can be made to change locale mid-flight: after
+// the serializer was constructed (and, before #5709 item 3, after it had
+// cached std::localeconv() for the whole call) but before a later float is
+// converted
+struct LocaleSwitchingStreambuf final : std::streambuf
+{
+    explicit LocaleSwitchingStreambuf(const char* switch_to)
+        : locale_after_first_write(switch_to)
+    {}
+
+    std::string data {}; // NOLINT(readability-redundant-member-init)
+    std::string locale_after_first_write;
+    bool switched = false;
+
+    std::streamsize xsputn(const char* s, std::streamsize n) override
+    {
+        if (!switched)
+        {
+            switched = std::setlocale(LC_NUMERIC, locale_after_first_write.c_str()) != nullptr;
+        }
+        data.append(s, static_cast<std::size_t>(n));
+        return n;
+    }
+};
+} // namespace
+
+TEST_CASE("locale changes during a single dump() (#5709 item 3)")
+{
+    // dump_float() only reads the locale on the snprintf path, taken for a
+    // number_float_t that is not an IEEE-754 single or double, i.e. not
+    // (is_iec559 && digits == 24 && max_exponent == 128) and not (is_iec559
+    // && digits == 53 && max_exponent == 1024) - see dump_float(). Checking
+    // is_iec559 alone is not enough: on x86_64, long double is a 64-bit
+    // (80-bit extended) format for which is_iec559 is also true, so it still
+    // takes the snprintf path this test means to exercise. Only a
+    // number_float_t whose digits/max_exponent match float or double (e.g.
+    // long double on 64-bit Arm, where it is IEEE-754 double) takes the
+    // locale-independent to_chars() path instead, and this test is a no-op
+    // there.
+    using long_double_json = nlohmann::basic_json<std::map, std::vector, std::string, bool, std::int64_t, std::uint64_t, long double>;
+    using ld_limits = std::numeric_limits<long_double_json::number_float_t>;
+    const bool is_ieee_single_or_double =
+        (ld_limits::is_iec559 && ld_limits::digits == 24 && ld_limits::max_exponent == 128) ||
+        (ld_limits::is_iec559 && ld_limits::digits == 53 && ld_limits::max_exponent == 1024);
+    if (is_ieee_single_or_double)
+    {
+        MESSAGE("long double is IEEE-754 single or double on this platform; dump_float()'s snprintf/locale path is not exercised here");
+    }
+
+    const char* de_DE_name = "de_DE.UTF-8";
+    if (std::setlocale(LC_NUMERIC, de_DE_name) == nullptr)
+    {
+        de_DE_name = "de_DE";
+        if (std::setlocale(LC_NUMERIC, de_DE_name) == nullptr)
+        {
+            MESSAGE("locale de_DE is not usable");
+            return;
+        }
+    }
+    const std::string decimal_point = std::localeconv()->decimal_point;
+    REQUIRE(std::setlocale(LC_NUMERIC, "C") != nullptr);
+    if (decimal_point != ",")
+    {
+        MESSAGE("de_DE's decimal point is not ',' on this platform, skipping");
+        return;
+    }
+
+    // a string long enough to overflow the serializer's internal write
+    // buffer, so that it is flushed to the output adapter - and the locale
+    // switched - before the number after it is converted
+    const std::string padding(5000, 'a');
+    const long_double_json j = { padding, 1234.5L };
+
+    LocaleSwitchingStreambuf buf(de_DE_name);
+    std::ostream os(&buf);
+    os << j;
+    CHECK(std::setlocale(LC_NUMERIC, "C") != nullptr);
+
+    REQUIRE(buf.switched);
+    // whatever locale was in effect when the float was actually converted,
+    // the output is normalized to use '.' as the decimal point: it must be
+    // looked up at conversion time, not once for the whole dump() - the same
+    // fix #5597 made on the parser side
+    CHECK(buf.data == "[\"" + padding + "\",1234.5]");
+}

tests/src/unit-merge_patch.cpp

@@ -305,10 +305,10 @@ TEST_CASE("JSON Merge Patch on deeply nested values")
         // over (detail::recursion_depth_limit(), 128)
         for (std::size_t depth = 0; depth <= 300; ++depth)
         {
-            CAPTURE(depth);
+            CAPTURE(depth)
             for (int variant = 0; variant < 3; ++variant)
             {
-                CAPTURE(variant);
+                CAPTURE(variant)
                 const json patch = json::parse(nested_objects(depth, variant));
 
                 json result = json::parse(nested_objects(depth, (variant + 1) % 3));
@@ -403,7 +403,7 @@ TEST_CASE("merge_patch() with an argument that aliases *this (#5641)")
                     std::size_t{0}, std::size_t{127}, std::size_t{128}, std::size_t{300}
                 })
         {
-            CAPTURE(depth);
+            CAPTURE(depth)
             json j = json::parse(nested_objects(depth, 0));
             const json expected = j;
             j.merge_patch(j);

tests/src/unit-modifiers.cpp

@@ -1084,10 +1084,10 @@ TEST_CASE("update() on deeply nested values")
         // over (detail::recursion_depth_limit(), 128)
         for (std::size_t depth = 0; depth <= 300; ++depth)
         {
-            CAPTURE(depth);
+            CAPTURE(depth)
             for (int variant = 0; variant < 3; ++variant)
             {
-                CAPTURE(variant);
+                CAPTURE(variant)
                 const json source = json::parse(nested_objects(depth, variant));
                 json result = json::parse(nested_objects(depth, (variant + 1) % 3));
                 json expected = result;
@@ -1177,7 +1177,7 @@ TEST_CASE("update() with an argument that aliases *this (#5641)")
                     std::size_t{0}, std::size_t{127}, std::size_t{128}, std::size_t{300}
                 })
         {
-            CAPTURE(depth);
+            CAPTURE(depth)
             json j = json::parse(nested_objects(depth, 0));
             const json expected = j;
             j.update(j, true);

tests/src/unit-msgpack.cpp

@@ -21,85 +21,11 @@ using nlohmann::json;
 #include <limits>
 #include <set>
 #include "make_test_data_available.hpp"
+#include "round_trip_corpus.hpp"
 #include "test_utils.hpp"
+#include "sax_countdown.hpp"
+using utils::SaxCountdown;
 
-namespace
-{
-class SaxCountdown
-{
-  public:
-    explicit SaxCountdown(const int count) : events_left(count)
-    {}
-
-    bool null()
-    {
-        return events_left-- > 0;
-    }
-
-    bool boolean(bool /*unused*/)
-    {
-        return events_left-- > 0;
-    }
-
-    bool number_integer(json::number_integer_t /*unused*/)
-    {
-        return events_left-- > 0;
-    }
-
-    bool number_unsigned(json::number_unsigned_t /*unused*/)
-    {
-        return events_left-- > 0;
-    }
-
-    bool number_float(json::number_float_t /*unused*/, const std::string& /*unused*/)
-    {
-        return events_left-- > 0;
-    }
-
-    bool string(std::string& /*unused*/)
-    {
-        return events_left-- > 0;
-    }
-
-    bool binary(std::vector<std::uint8_t>& /*unused*/)
-    {
-        return events_left-- > 0;
-    }
-
-    bool start_object(std::size_t /*unused*/)
-    {
-        return events_left-- > 0;
-    }
-
-    bool key(std::string& /*unused*/)
-    {
-        return events_left-- > 0;
-    }
-
-    bool end_object()
-    {
-        return events_left-- > 0;
-    }
-
-    bool start_array(std::size_t /*unused*/)
-    {
-        return events_left-- > 0;
-    }
-
-    bool end_array()
-    {
-        return events_left-- > 0;
-    }
-
-    bool parse_error(std::size_t /*unused*/, const std::string& /*unused*/, const json::exception& /*unused*/) // NOLINT(readability-convert-member-functions-to-static)
-    {
-        return false;
-    }
-
-  private:
-    int events_left = 0;
-};
-} // namespace
 
 TEST_CASE("MessagePack")
 {
@@ -1614,19 +1540,39 @@ TEST_CASE("MessagePack")
             CHECK_THROWS_WITH_AS(_ = json::from_msgpack(std::vector<uint8_t>({0x81})), "[json.exception.parse_error.110] parse error at byte 2: syntax error while parsing MessagePack string: unexpected end of input", json::parse_error&);
         }
 
-        SECTION("invalid UTF-8 in string (see #5529)")
+        SECTION("ill-formed UTF-8 in string (see #5529, #5651)")
         {
+            // the MessagePack specification explicitly allows a str object to
+            // contain a byte sequence that is not valid UTF-8 and expects a
+            // deserializer to hand the original bytes back unchanged; this
+            // library follows that, unlike CBOR/UBJSON/BJData/BSON, whose
+            // specifications require text strings to be valid UTF-8
+
             // a fixstr of length 2 (0xA0 | 2) whose bytes are not valid UTF-8
-            // (0xC0 0xAE is an overlong encoding of '.') must be rejected at
-            // decode time, matching every other kind of malformed binary
-            // input, rather than only failing later when the resulting
-            // value is dumped
-            json _;
-            CHECK_THROWS_WITH_AS(_ = json::from_msgpack(std::vector<uint8_t>({0xa2, 0xc0, 0xae})), "[json.exception.parse_error.113] parse error at byte 3: syntax error while parsing MessagePack string: invalid string: ill-formed UTF-8 byte", json::parse_error&);
-            CHECK(json::from_msgpack(std::vector<uint8_t>({0xa2, 0xc0, 0xae}), true, false).is_discarded());
+            // (0xC0 0xAE is an overlong encoding of '.') round-trips byte for
+            // byte as a string value
+            const std::vector<uint8_t> ill_formed_value = {0xa2, 0xc0, 0xae};
+            json j_value;
+            CHECK_NOTHROW(j_value = json::from_msgpack(ill_formed_value));
+            REQUIRE(j_value.is_string());
+            CHECK(j_value.get_ref<const json::string_t&>() == std::string("\xc0\xae"));
+            CHECK(json::from_msgpack(json::to_msgpack(j_value)) == j_value);
+            // dump() still requires valid UTF-8 and throws for such a value,
+            // unless an error handler that replaces or ignores the bytes is
+            // passed
+            CHECK_THROWS_AS(j_value.dump(), json::type_error&);
+
+            // the same bytes as an object key round-trip as well
+            const std::vector<uint8_t> ill_formed_key = {0x81, 0xa2, 0xc0, 0xae, 0x01};
+            json j_key;
+            CHECK_NOTHROW(j_key = json::from_msgpack(ill_formed_key));
+            REQUIRE(j_key.is_object());
+            CHECK(j_key.contains(std::string("\xc0\xae")));
+            CHECK(json::from_msgpack(json::to_msgpack(j_key)) == j_key);
 
             // a MessagePack bin8 blob with the very same bytes is NOT text
             // and must still be accepted as-is
+            json _;
             CHECK_NOTHROW(_ = json::from_msgpack(std::vector<uint8_t>({0xc4, 0x02, 0xc0, 0xae})));
             CHECK(_ == json::binary(std::vector<std::uint8_t>({0xc0, 0xae})));
 
@@ -1930,6 +1876,38 @@ TEST_CASE("Parse MessagePack directly from a file using iterator and sentinel")
     CHECK((parsed.is_object() || parsed.is_array()));
 }
 
+TEST_CASE("MessagePack round-trip invariants")
+{
+    // This checks what the parse_msgpack_fuzzer driver checks (see
+    // tests/src/fuzzer-parse_msgpack.cpp), so that a regression shows up in
+    // CI rather than as an OSS-Fuzz report: anything from_msgpack() returns
+    // (j1) can be serialized, parsed back (j2), and serialized again to
+    // reproduce the exact bytes.
+    for (const auto& j0 : utils::round_trip_corpus::values())
+    {
+        json j1;
+        try
+        {
+            // turn the corpus value into a value as from_msgpack() returns it
+            j1 = json::from_msgpack(json::to_msgpack(j0));
+        }
+        catch (const json::exception&)
+        {
+            // the fuzzer driver only ever sees values from_msgpack() actually
+            // produced, so skip corpus values that do not survive the
+            // round trip here, too
+            continue;
+        }
+
+        INFO("j1 = " << j1.dump());
+        const std::vector<std::uint8_t> vec = json::to_msgpack(j1);
+        json j2;
+        // anything the library writes must be parsable by the library
+        REQUIRE_NOTHROW(j2 = json::from_msgpack(vec));
+        CHECK(json::to_msgpack(j2) == vec);
+    }
+}
+
 TEST_CASE("MessagePack roundtrips" * doctest::skip())
 {
     SECTION("input from msgpack-python")

tests/src/unit-precise-stream-position.cpp

@@ -113,7 +113,7 @@ TEST_CASE("JSON_PRECISE_STREAM_POSITION")
 
         for (const auto& test : tests)
         {
-            CAPTURE(test.first);
+            CAPTURE(test.first)
             std::istringstream ss(test.first);
             json j;
             ss >> j;
@@ -135,7 +135,7 @@ TEST_CASE("JSON_PRECISE_STREAM_POSITION")
 
         for (const auto& test : tests)
         {
-            CAPTURE(test.first);
+            CAPTURE(test.first)
             std::istringstream ss(test.first);
             json j;
             ss >> j;
@@ -149,7 +149,7 @@ TEST_CASE("JSON_PRECISE_STREAM_POSITION")
                 {"1", "12", "-3.5e2", " 7 "
                 })
         {
-            CAPTURE(s);
+            CAPTURE(s)
             std::istringstream ss(s);
             json j;
             ss >> j;

tests/src/unit-readme.cpp

@@ -28,7 +28,7 @@ using nlohmann::json;
 DOCTEST_MSVC_SUPPRESS_WARNING_PUSH
 DOCTEST_MSVC_SUPPRESS_WARNING(4189)
 
-TEST_CASE("README" * doctest::skip())
+TEST_CASE("README")
 {
     {
         // redirect std::cout for the README file

tests/src/unit-regression1.cpp

@@ -1482,7 +1482,23 @@ TEST_CASE("regression tests 1")
 
     SECTION("issue #972 - Segmentation fault on G++ when trying to assign json string literal to custom json type")
     {
+        // this assignment used to crash outright
         my_json const foo = R"([1, 2, 3])"_json;
+
+        // fifo_map is the adapter the docs recommend for keeping object keys
+        // in insertion order (see docs/mkdocs/docs/features/object_order.md
+        // and docs/mkdocs/docs/features/types/template_parameters.md); check
+        // that recommendation actually holds, including through erase() and
+        // inserting a new key. The comparator is stateful, so this avoids
+        // deep copies of "order" (see #1763, #5649).
+        my_json order = my_json::parse(R"({"z":1,"a":2,"m":{"y":1,"b":2}})");
+        CHECK(order.dump() == R"({"z":1,"a":2,"m":{"y":1,"b":2}})");
+
+        order.erase("z");
+        CHECK(order.dump() == R"({"a":2,"m":{"y":1,"b":2}})");
+
+        order["new_key"] = 3;
+        CHECK(order.dump() == R"({"a":2,"m":{"y":1,"b":2},"new_key":3})");
     }
 
     SECTION("issue #977 - Assigning between different json types")